{
  "assessedAt": "2026-10-21",
  "sourceCommit": "f245136a",
  "method": "本次全量重新采集和 v3 逐图评分前的原始绑定与评分；不覆盖历史审阅。",
  "rubric": {
    "version": 2,
    "kind": "screenshot",
    "dimensionMaximums": {
      "taskCoverage": 40,
      "composition": 20,
      "readability": 15,
      "interactionClarity": 10,
      "craft": 15
    },
    "taskCheckMaximum": 10,
    "stateCeilings": {
      "result": 100,
      "initial": 100,
      "partial": 100,
      "blocked": 39
    },
    "tasks": {
      "bluebook/v1": {
        "promptHash": "bfc111eab2e9374f5f9db6d7ddb0754fb0b7e0ef81a13f4ba87cbf642a0f0ef0",
        "checks": [
          {
            "id": "masonry",
            "label": "多列错落图片流",
            "description": "可辨图片、高度变化和桌面四列任务布局；不能从截图判定图片来源或懒加载实现。"
          },
          {
            "id": "cardFields",
            "label": "卡片信息",
            "description": "标题、圆形文字头像昵称、点赞图标和计数可见。"
          },
          {
            "id": "header",
            "label": "搜索与发布",
            "description": "品牌、搜索输入和发布入口明确。"
          },
          {
            "id": "visualContract",
            "label": "任务视觉约定",
            "description": "清新简洁、浅灰底白卡、红色主操作、圆角和图文社交结构；不强制摄影风格，v2允许mock图像。"
          }
        ]
      },
      "bluebook/v2": {
        "promptHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "checks": [
          {
            "id": "masonry",
            "label": "多列错落图片流",
            "description": "可辨图片、高度变化和桌面四列任务布局；不能从截图判定图片来源或懒加载实现。"
          },
          {
            "id": "cardFields",
            "label": "卡片信息",
            "description": "标题、圆形文字头像昵称、点赞图标和计数可见。"
          },
          {
            "id": "header",
            "label": "搜索与发布",
            "description": "品牌、搜索输入和发布入口明确。"
          },
          {
            "id": "visualContract",
            "label": "任务视觉约定",
            "description": "清新简洁、浅灰底白卡、红色主操作、圆角和图文社交结构；不强制摄影风格，v2允许mock图像。"
          }
        ]
      },
      "circuit-lab/v1": {
        "promptHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "checks": [
          {
            "id": "circuit",
            "label": "可辨电路",
            "description": "元件符号、端子和连线形成可阅读的电路；空网格不算电路成果。"
          },
          {
            "id": "editor",
            "label": "编辑器覆盖",
            "description": "电池、电阻、开关、灯泡的工具和属性入口可见；不把按钮存在视为已验证功能。"
          },
          {
            "id": "measurements",
            "label": "数值结果",
            "description": "元件电压电流方向及状态可与图示核对；0.04A等可见读数只证明该截图状态。"
          },
          {
            "id": "presets",
            "label": "预设与说明",
            "description": "串联并联、重置和必要的操作与简化模型说明可见。"
          }
        ]
      },
      "fantasy-map-generator/v1": {
        "promptHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "checks": [
          {
            "id": "terrain",
            "label": "地貌层次",
            "description": "海洋海岸、平原、森林和山脉有清楚区分。"
          },
          {
            "id": "waterways",
            "label": "水系与聚落",
            "description": "河流湖泊与城镇可辨且图示关系自然；不由静态图证明水文算法。"
          },
          {
            "id": "controls",
            "label": "地图操作覆盖",
            "description": "种子、地形参数、画笔、平移缩放、标签和导出入口可见。"
          },
          {
            "id": "mapStyle",
            "label": "地图表达",
            "description": "手绘式地图符号、图例、边界和自然地形；不额外奖励装饰标题。"
          }
        ]
      },
      "fluid-simulation/v1": {
        "promptHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "checks": [
          {
            "id": "dye",
            "label": "染料形态",
            "description": "画布中有可辨染料及连续卷曲或扩散形态；光点不等同完整流态。"
          },
          {
            "id": "mixing",
            "label": "流态层次",
            "description": "细节、不同颜色交汇和层次可辨；单色和早期注入只按已展示内容计。"
          },
          {
            "id": "parameters",
            "label": "求解参数覆盖",
            "description": "颜色、力度、耗散、迭代和分辨率控制可见。"
          },
          {
            "id": "operation",
            "label": "运行状态覆盖",
            "description": "暂停继续、清空重置、截图和操作/兼容状态说明可见；不验证求解方程或FPS。"
          }
        ]
      },
      "life-diary/v1": {
        "promptHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "checks": [
          {
            "id": "diary",
            "label": "情绪与日记流程",
            "description": "情绪记录、编辑、内容与回顾页面有具体界面。"
          },
          {
            "id": "ai",
            "label": "AI陪伴呈现",
            "description": "AI对话、整理或洞察有具体内容，不只一个入口或规划文字。"
          },
          {
            "id": "assistant",
            "label": "生活助手覆盖",
            "description": "生活计划、趋势、习惯或个人管理有具体界面。"
          },
          {
            "id": "mobile",
            "label": "移动原型完整性",
            "description": "多个独立iPhone尺寸页面、导航和组件一致；只按截图展开的页面评分。"
          }
        ]
      },
      "meditation/v1": {
        "promptHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "checks": [
          {
            "id": "discovery",
            "label": "场景与课程",
            "description": "首页、课程发现及内容信息体现真实冥想场景。"
          },
          {
            "id": "practice",
            "label": "练习流程",
            "description": "播放器、计时、呼吸或练习进行状态有具体界面。"
          },
          {
            "id": "support",
            "label": "持续使用流程",
            "description": "睡眠、完成反馈、进度或个人设置等页面可见。"
          },
          {
            "id": "ios",
            "label": "iOS原型表达",
            "description": "独立移动屏、摄影素材、导航与组件形成完整原型。"
          }
        ]
      },
      "neo-gothic-tower-city/v1": {
        "promptHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "checks": [
          {
            "id": "gothicForm",
            "label": "哥特建筑形态",
            "description": "尖塔、纵向立面、拱形或窗饰等具有可辨哥特特征，而非普通方楼加锥顶。"
          },
          {
            "id": "cityLayout",
            "label": "城市场景",
            "description": "建筑群、街巷、平台或桥梁形成有层次的3D城市；孤立塔楼不等同城市。"
          },
          {
            "id": "architecture",
            "label": "建筑细节",
            "description": "窗饰、层次、构件和楼型差异可见；HUD的比例数字不证明真实比例。"
          },
          {
            "id": "context",
            "label": "场景与漫游线索",
            "description": "环境、城市空间与可漫游操作线索清楚；粒子数量不自动加分。"
          }
        ]
      },
      "pathfinding-lab/v1": {
        "promptHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "checks": [
          {
            "id": "grid",
            "label": "网格与地形",
            "description": "起终点、障碍和高代价格可辨；空网格可体现编辑器初始态但非完整地形展示。"
          },
          {
            "id": "editing",
            "label": "算法与编辑覆盖",
            "description": "BFS/Dijkstra/A*、画笔、预设、运行暂停单步等入口可见。"
          },
          {
            "id": "search",
            "label": "搜索可视化",
            "description": "前沿、访问和最终路径或明确不可达结果可见；未运行态只按可见状态计。"
          },
          {
            "id": "cost",
            "label": "图例与结果",
            "description": "步数、代价和图例、不同算法规则明确；数值不证明所有算法正确。"
          }
        ]
      },
      "pixel-flow/v1": {
        "promptHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "checks": [
          {
            "id": "imageParticles",
            "label": "图片与粒子成果",
            "description": "有粒子场，图像重构轮廓更充分；任意散点/景深光斑不能替代可辨原图。"
          },
          {
            "id": "imageInput",
            "label": "图片输入覆盖",
            "description": "本地上传、采样、打散/还原和进度状态明确。"
          },
          {
            "id": "camera",
            "label": "相机追踪证据",
            "description": "相机入口与画面区域可计少量覆盖；实际视频或手部关键点缺失时最高4分。"
          },
          {
            "id": "gestures",
            "label": "手势与反馈覆盖",
            "description": "具体手势说明、状态和还原反馈；纯按钮/文字说明而无追踪状态时最高7分。"
          }
        ]
      },
      "stock-watching/v1": {
        "promptHash": "e0a5e7cc44cbc1324398c97efe6bf9db2368cd3cd46795e1d3f1d259cc669033",
        "checks": [
          {
            "id": "quotes",
            "label": "行情与市场",
            "description": "行情字段、自选合约与市场切换可见。"
          },
          {
            "id": "crud",
            "label": "合约管理",
            "description": "增删改查对应界面及状态可见。"
          },
          {
            "id": "errors",
            "label": "异常与校验",
            "description": "网络或服务不可用提示及数据校验反馈可见。"
          },
          {
            "id": "app",
            "label": "应用界面",
            "description": "完整可读的前端布局；不从截图判断后端或数据库实现。"
          }
        ]
      },
      "voxel-construction-site/v1": {
        "promptHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "checks": [
          {
            "id": "zones",
            "label": "工地分区",
            "description": "基坑、在建楼、棚区、物料、板房和道路等有序可辨。"
          },
          {
            "id": "machinery",
            "label": "机械与人员",
            "description": "塔吊、挖掘机、车辆、工人及施工细节可辨；静态图不证明动画或碰撞。"
          },
          {
            "id": "tabletop",
            "label": "桌面场景",
            "description": "室内木桌、蓝图工具道具及实体控制线索形成微缩沙盘，观察角度适合总览。"
          },
          {
            "id": "voxel",
            "label": "体素表达",
            "description": "方块颗粒、比例、施工构件与丰富细节明确；平滑大体块不等于充分体素细节。"
          }
        ]
      },
      "youtube-ui/v1": {
        "promptHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "checks": [
          {
            "id": "flow",
            "label": "当前功能流程",
            "description": "当前模块的相关页面和状态具体连贯；不强行要求一次展示所有模块。"
          },
          {
            "id": "content",
            "label": "内容与素材",
            "description": "视频/业务内容、摄影素材和元数据具体；上传等无封面状态不机械扣图像分。"
          },
          {
            "id": "mockups",
            "label": "独立页面展示",
            "description": "同一功能相关页面有独立mockup边界与并排展示，避免规划文字代替界面。"
          },
          {
            "id": "mobile",
            "label": "App组件结构",
            "description": "移动端导航、信息架构和组件规范清楚；历史APP业务上下文缺失不补造。"
          }
        ]
      }
    }
  },
  "runs": [
    {
      "id": "bluebook--claude-4-0-unknown-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 7,
          "header": 10,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "f34bae21621fc17cdb8e11eb791890a4aecb96e3ec071732d1b32ba402e7ac01",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列摄影内容和搜索发布清楚；作者区缺少明显的圆形文字头像，昵称与点赞偏小，部分文案重复。"
      }
    },
    {
      "id": "bluebook--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 61,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 10,
          "readability": 10,
          "interactionClarity": 6,
          "craft": 8
        },
        "taskChecks": {
          "masonry": 4,
          "cardFields": 7,
          "header": 8,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e36c68b1e121f9ae6fa473a97713275d16543c188b9fb9731d2aa5ce1dad125e",
        "screenshotHash": "2e6079d6c43cb2582ea0f80547642c8ffbd80a3da66be6850e6b30ea7160df6a",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "摄影卡片与搜索发布可辨，但桌面截图仅中间很窄的三列内容，左右留白过多，头像及点赞信息层级偏弱。"
      }
    },
    {
      "id": "bluebook--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "masonry": 8,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "5b83a62018666a623f0192b736b4f5b946847b28f60b684c5f98b9ddd8f95d2b",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列高低不同的粉彩封面与作者点赞可见，搜索发布齐全；封面由圆和横条反复组成，视觉内容区分度较弱。"
      }
    },
    {
      "id": "bluebook--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7241e19f984de35228aadf84f4ec30816b6e6cdcecadb1464eed46358f604bcc",
        "screenshotHash": "e6d342df59ac3d41f6a4523047a7e7470f6ec0200f301685293bad5959aa3d52",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "蛋糕、猫、海岛等插画构成错列图片流，搜索发布与作者点赞齐备；插画有辨识度，少量标题拥挤。"
      }
    },
    {
      "id": "bluebook--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "064fb1b545573a65f67711533fc7a6888e4bb30c10b1ed19a4b6a5d115374ab0",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "气泡渐变封面与文字头像、点赞完整，一张卡片明确显示图片加载失败回退；回退图标过大，封面主题重复。"
      }
    },
    {
      "id": "bluebook--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "be76ff6a8dba287f7ad910e0f376eb11a0fd5726718d535f6633242ea065ebde",
        "screenshotHash": "c5fed172fb25ac9c2ecab284a1cc3dff027bff7da73a14dc68ed9bdafb5a350c",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "封面高度和几何景物有变化，搜索发布、文字头像与点赞可辨；辅助信息较淡，插画模板重复。"
      }
    },
    {
      "id": "bluebook--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "masonry": 8,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "44687b96d043d3156cb0958a1d95595f076b453a209c47373410cd426c29d254",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列彩色插画流和完整卡片元数据可见；长截图下部出现大片未加载图片和分散文本，展示完整性不足。"
      }
    },
    {
      "id": "bluebook--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "1fd26d4c8708401342721e4374325817e8a108db29ecaa00bb44e26c9086a56c",
        "screenshotHash": "9ca25a17478b9bee26c9541ed3d94a9d8be7179b4429777658d720bd51b5e0b5",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列高低错落卡片、完整标题/文字头像/昵称/点赞及搜索发布入口清楚，浅灰底白卡与红色主操作符合任务。mock 抽象图可以用于 v2，不因没有摄影扣分；第二列末卡图像区域未展开，图片造型重复较多、浅灰元信息对比偏弱。截图不能验证懒加载和无限滚动。"
      }
    },
    {
      "id": "bluebook--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "masonry": 10,
          "cardFields": 10,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "92ed572a02b6b15fcb6d6fa375e7630788b0b3e8256d09e331e0bd80086b09a4",
        "screenshotHash": "97cdc0ffbe7169e8cbfad25cabf156140e906f1796489a05fcffa415c4081a59",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "桌面四列瀑布流高度错落，封面为颜色与摄影、餐具等符号组合的程序化插画；标题、圆形文字头像、昵称、心形图标和数量均清楚，搜索与红色发布入口可辨。v2 允许 mock 图片，按可见图像评价；封面重复使用少量抽象母题，视觉细节变化有限。截图不证明懒加载、无限滚动或点赞动画。"
      }
    },
    {
      "id": "bluebook--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "masonry": 8,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "e30234c63eb630dd983e5424e8237a1665b22f71e4c7010031dd53b7a367d7aa",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列错落图片、标题和作者点赞信息可见；长截图下半段保留多块未加载图片区，细小元数据和大面积空卡影响完成度。"
      }
    },
    {
      "id": "bluebook--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 56,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 7,
          "readability": 11,
          "interactionClarity": 7,
          "craft": 4
        },
        "taskChecks": {
          "masonry": 4,
          "cardFields": 8,
          "header": 9,
          "visualContract": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "eeec93362352502d3401c648906819912c31730a543eeebb309e51645c536639",
        "screenshotHash": "25829ac048747050b334dcd7fb7fa340f21ac098bbcc6b7ca3e8b47d89f67e19",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "顶部搜索发布与卡片信息可见，但图片下方出现异常高的空白区域，卡片纵向节奏断裂，部分头像呈破图状态。"
      }
    },
    {
      "id": "bluebook--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "f62414b16f01ac274e694a3ae1543e2ff7053f7ba51bde56816582e20bc81452",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "摄影瀑布流、两行标题、文字头像、搜索发布均清晰，信息密度适中；个别素材与文案重复。"
      }
    },
    {
      "id": "bluebook--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "eab9a270284d8a237e395cc17cf2bbfd056e23c5643fd642a1769f02c6462512",
        "screenshotHash": "042cfe5c742546c321c364a724dd58791641a2236a7665c1caecb0387cd62add",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "粉彩封面、分类与发布搜索齐备，作者点赞布局统一；首排和次排高度趋同，瀑布流变化及内容区分度有限。"
      }
    },
    {
      "id": "bluebook--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 8,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "094d000032805e2a6f5d5d699c0886574ad9398d9c93447f6bbb21779926db9e",
        "screenshotHash": "df728fe11e6266a6e41044e0d6f2f570100cb5c2e21953c8a9df3c576689269f",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "品牌横幅、分类与四列图文流完整成形，首段摄影内容清晰；截图后半段图片仍为灰色加载块，重复内容较多。"
      }
    },
    {
      "id": "bluebook--gpt-6-1-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e7ff97eb6e6760d5376d9749de9df2c62db707a55e8a19cec2d70f6647f8a314",
        "screenshotHash": "50ce0e0843f5aae44b8dbdc127b1ed373ca05026632582a3472dfce688094fc7",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "标题、分类、搜索和发布形成清楚层级，山景插画卡片配文字头像与点赞；插画和文案重复较多。"
      }
    },
    {
      "id": "bluebook--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "91d1c98eb8a938ac29a5aed21dd654ba24a315619eff23cbaada70e81a9df0e8",
        "screenshotHash": "d6aaf49060e34939da0ecf2f9fb4a5bc6a52d230db3e9bf9cb60f9d4bb016f4d",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "品牌标题、分类、搜索发布和作者点赞完整，低饱和插画与错列卡片统一；少量辅助文字偏淡。"
      }
    },
    {
      "id": "bluebook--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 94,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "0727680c8cf4ec3483cbee4880d9eecf21cda513415799316cd55bc67fc9e974",
        "screenshotHash": "168386402d146a2e7b9b0b569c269e3285a80128904e417eef29487ccc34a4d5",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列摄影瀑布流、完整标题/头像/作者/点赞字段、搜索和红色发布按钮均清楚，灰底白卡与选中态统一。首行图片高度差较小，作者和点赞计数字号偏小；下方卡片自然延续到画外不另扣分。仅评价可见排版，不由静态图验证懒加载或点赞动画。"
      }
    },
    {
      "id": "bluebook--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "77fac8ce98caf31de1b4ab775ba6892390d7c40ec6672ae71186054e80aa0b38",
        "screenshotHash": "c671b9f860cb300eadeaadab9ce25e4d9b2954186f30adf5c3a444ac2990974e",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "摄影瀑布流、文字头像、点赞及搜索发布齐全，标题分类层级和图片节奏清楚；次级计数对比稍弱。"
      }
    },
    {
      "id": "bluebook--gpt-6-luna-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "284e66bd083c6b1cd8ee80c43a5c1aa0ec73ef2152c5588d57257f8187efbfdd",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列图片高低错落，搜索、发布、作者头像与点赞信息齐全；侧栏与内容层级明确，次级元数据略小。"
      }
    },
    {
      "id": "bluebook--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "masonry": 8,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "e6a67a1a1f09edbbbea677e584f7e9ca2d845b21a5eb72d7b34aea866e06b8d7",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "生活主题标题与分类清楚，粉彩封面和文字头像点赞样式统一；首排封面等高且主题变化偏少。"
      }
    },
    {
      "id": "bluebook--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 61,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 12,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 4
        },
        "taskChecks": {
          "masonry": 3,
          "cardFields": 8,
          "header": 9,
          "visualContract": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "51a14a52b39bb631a3b60ea4070e5267219745b9cc92f5e6c2a71e6b1bd6e6de",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "搜索发布、作者和点赞已经显示，但全部大图区域为空白，照片成果没有被截图记录；不能据此推断图片加载故障原因。"
      }
    },
    {
      "id": "bluebook--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "bfc111eab2e9374f5f9db6d7ddb0754fb0b7e0ef81a13f4ba87cbf642a0f0ef0",
        "screenshotHash": "27f6720159ed8fe93afca60513e213d128090b50b832d1722f65a3f42a7b9178",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "归档 PNG 只有整页浅色背景，没有任务界面或明确错误状态；无法从这张截图给出有依据的案例分数。"
      }
    },
    {
      "id": "bluebook--longcat-25-preview-free-default-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "27f6720159ed8fe93afca60513e213d128090b50b832d1722f65a3f42a7b9178",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "整张归档截图为空白浅色页面，没有品牌栏、图片卡片或错误说明；现有图像不足以判断案例呈现质量与空白原因。"
      }
    },
    {
      "id": "bluebook--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "eb7abb2a6ef34b2a1bde8878e14535c21a87b046dfb7d423fb888b17996e45d5",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "粉彩错列卡片、搜索发布、作者点赞与失败回退均可见；图片变化主要来自配色，图像内容较单一。"
      }
    },
    {
      "id": "bluebook--minimax-m2-1-unknown-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 9,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "bfc111eab2e9374f5f9db6d7ddb0754fb0b7e0ef81a13f4ba87cbf642a0f0ef0",
        "screenshotHash": "583994c87b2ce6da86eac8b62ad9cb714b09352c1091bb5e5b7b8325e25e236a",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "四列本地摄影素材、标题、文字头像和点赞齐备，列间节奏紧凑；顶部发布仅用加号表达，辅助信息略小。"
      }
    },
    {
      "id": "bluebook--minimax-m2-unknown-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 8,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "bfc111eab2e9374f5f9db6d7ddb0754fb0b7e0ef81a13f4ba87cbf642a0f0ef0",
        "screenshotHash": "1d5f6610510fd0afecf8cb8d1536f82ed171fb8e237e4fe5196c634461129d07",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "四列摄影图文、文字头像与点赞信息可见；卡片额外堆叠标签和多行描述，超出简洁标题卡片的任务尺度，信息较拥挤。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 10,
          "header": 10,
          "visualContract": 10
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "97ce5a1564d5040d6ce30ac181bfc2801c34a4526290da73cebf4caa5a5642d2",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列错落卡片、标题、圆形文字头像、昵称与心形计数齐备，搜索和红色发布入口完整，浅灰底白卡符合任务约定。第二列首图及第三列第二图仍是灰色占位，主要影响图片流覆盖；插画可按允许的 mock 素材评价，不因未用摄影扣分。间隙和对齐统一，次级文字偏小、偏浅，插画造型重复。静态截图不证明懒加载、点赞动画或下拉刷新。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 10,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "44b3202ea6def160d6e5f68060536f4106ce131642c976ef21025b153e18fd96",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "桌面四列错落图片流与卡片标题、文字头像、昵称、心形计数完整，品牌、搜索和红色发布按钮清楚。允许使用 mock 图像，不能仅因没有摄影扣任务分；主要限制是圆形叠加图案重复、作者文字与图标偏浅，首屏图像色块偏重。截图不能验证懒加载、刷新及点赞动画。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 10,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "3ca4b74039d34d47f79b9477f759a410e2f13822004f426323cddd156c8abcc4",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列高低错落的本地 SVG 图片卡片清楚可辨，含搜索、发布、文字头像、作者与点赞数，v2 允许 mock 图像。多张素材重复，标题与图像文字关联松散，卡片文字偏小且字形不统一；仅评价首屏，不从截图证明懒加载和刷新。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "8d2d1ecea2901efad146b5d488b9fdbf86919270393f0db6cbe1a3df13915e15",
        "screenshotHash": "e61bd20f86658427f3e793bf840999d7bb072647707e5a41f1c13ab2c934847e",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "摄影卡片高低变化、搜索和发布清晰，作者点赞信息齐全；多张相同照片和相似标题反复出现，内容精修不足。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "61e0d6280df62c43e5ca6a41eda5d11f9e491db9d55a18004fd9630336e88d73",
        "screenshotHash": "b7b37b6915f85008c76bc15eca2027c86f311df8aefac90eda0bcfdda117cde7",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "摄影四列错落、作者点赞和品牌搜索发布清楚；个别卡片图片重复，次级文本对比略弱。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "masonry": 9,
          "cardFields": 9,
          "header": 10,
          "visualContract": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "dc65bc38cbc79523c1913d45a1278c88b5e76d0468942ed6a88d4670bc3dbe0a",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "摄影图片错落排列，搜索发布与社交信息齐全；下缘仍有未载入灰块，部分图片与标题主题联系较弱。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-preview-max-r04",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 9,
          "header": 8,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "bfc111eab2e9374f5f9db6d7ddb0754fb0b7e0ef81a13f4ba87cbf642a0f0ef0",
        "screenshotHash": "603500e93450e593fa08160210e4eb4bd0fe6f26420410ba4891401ed9bc3459",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "四列彩色几何封面、作者点赞和底部导航可见；封面内容重复且少量标题贴边，发布入口较弱。"
      }
    },
    {
      "id": "bluebook--minimax-m3-1-flash-preview-max-r05",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 9,
          "header": 8,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "45d879da2b75a1e6a489dc6ef862c3c428ca51d96a5ed8faaf7b31685120849c",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "彩色几何封面、作者文字头像、点赞及底部导航可见；封面构成重复，发布入口弱，桌面卡片偏大且信息稀疏。"
      }
    },
    {
      "id": "bluebook--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 16,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "bfc111eab2e9374f5f9db6d7ddb0754fb0b7e0ef81a13f4ba87cbf642a0f0ef0",
        "screenshotHash": "af878198b60dccbd399aab35f234fd82167b0bf3a2ed2c67b9c67ae539f368c4",
        "criteriaHash": "5760964ba6951e286eae0078c5d84c9c82256921916620d47fff33833572edaf",
        "evidence": "搜索发布、文字头像和点赞齐备，彩色文字封面清楚；首屏接近整齐网格，瀑布流高度变化不足，封面模板重复。"
      }
    },
    {
      "id": "bluebook--minimax-m3-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 15,
          "readability": 13,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "f71bb49d7ca2b12f14c597e7df57222e1682483d00f04d7a2615973ad4d894c6",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "彩色文字封面与卡片信息可辨，搜索发布位置清楚；若干图片仅显示灰块，内容密度和图片完成状态不一致。"
      }
    },
    {
      "id": "bluebook--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 12,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 5
        },
        "taskChecks": {
          "masonry": 5,
          "cardFields": 8,
          "header": 9,
          "visualContract": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "982f36f45e45e5a97c6cb1173f9b53ac298865446853e6a053df22c6e6daedaf",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "搜索发布与卡片作者点赞已呈现，但多张卡片大图为灰块，空图与已载入摄影交错，图片流不完整。"
      }
    },
    {
      "id": "bluebook--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "masonry": 8,
          "cardFields": 9,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6bba5cdbe7b5246b7b20cadac014952870b4f66ddc27d3edbc00a8fa9808876a",
        "screenshotHash": "6a8afa8e6cbdd3c836459662549a0e479d8f97f0058b02dbc68e09a9c36657b2",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列粉彩卡片与失败回退明确，标题作者点赞完整；长截图末段保留多块空白待载入区域，完成状态不统一。"
      }
    },
    {
      "id": "bluebook--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 9
        },
        "taskChecks": {
          "masonry": 7,
          "cardFields": 8,
          "header": 9,
          "visualContract": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "ff7187072518233243bfb61302fa8951da81c1d96e5fb2ffe919e760d87941df",
        "screenshotHash": "5338cc385671b1b94ba40a7a84898d709287dd63f8e511cc3e53fc62275e81aa",
        "criteriaHash": "f4c2fedb94b5333b9aa5e0c9ad0601f2370b1291c79bd4c359ed29af49c7e33c",
        "evidence": "四列粉彩几何图片和卡片信息清楚，搜索发布齐全；首排近似等高，内容变化有限，社交元数据偏小。"
      }
    },
    {
      "id": "circuit-lab--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "d25267decaa2c40dcacc67c5d24fada36f5081055c971af7e6112c0dc7e2e974",
        "screenshotHash": "5727ab5debf9333fc88b092cb05fc2cf5cc2b07969499fd16c3f20b9efc21333",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "截图仅有居中的小型元件工具和空网格，没有电路与结果；不能把待搭建状态认定为功能失败。"
      }
    },
    {
      "id": "circuit-lab--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 9,
          "measurements": 8,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "48cc0e7a29de2e83fa98feefab0c9d947a9e5d584a9ca0254d8c7f20ed2bdfae",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "电源、电阻和开关卡片显示读数，预设与操作说明可见；回路形状不够规整，较长导线交错且次级文字偏小。"
      }
    },
    {
      "id": "circuit-lab--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "circuit": 10,
          "editor": 10,
          "measurements": 10,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "475e4587d9defb7d04f8f49737a50c447ff3b3e9f0f0118d2948c9af56e8c4eb",
        "screenshotHash": "25615f12b054ff56c94b765129d290f20c5738273ada75142354ab066fb8516b",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "标准回路符号与节点清楚，100Ω和200Ω分别标4V和8V、0.04A，工具、结果、操作和模型说明分区明确。"
      }
    },
    {
      "id": "circuit-lab--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "e2e3db63782f5cb7d7a4c2d3bf5b256552cd84bfa3b452933b0bac719174e29f",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "串联回路、方向箭头、0.04A与结果表对应明确；线路三角布局较松，操作说明字号偏小。"
      }
    },
    {
      "id": "circuit-lab--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 13,
          "readability": 9,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 10,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7feef718c9532bf9406f6be8d60e5fae26159f3680b6d7a4bfd62dbaa06bd1f0",
        "screenshotHash": "f407f899f70bf36ee87f34ca0b68b9a9c34c87bd40801aef32b1af21e4f0cacf",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "串联回路、元件工具和结果表完整；电路占画布比例很小，细线与读数难读，下半屏大幅空置。"
      }
    },
    {
      "id": "circuit-lab--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 15,
          "readability": 10,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 10,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "ae3b329dd767d334ac6a09f6b9c296450bfb46ad753f3748f1ee33f908e7f9c6",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "元件工具、串并联预设和串联结果齐全，彩色连线可辨；符号与数值偏细，侧栏和下半屏空间利用欠均衡。"
      }
    },
    {
      "id": "circuit-lab--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 17,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "circuit": 7,
          "editor": 8,
          "measurements": 9,
          "presets": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "1236378aeb97552ce780604b79e00434ff4e63946f3552173534eeecb1162bba",
        "screenshotHash": "f93682a42e42a0778f9ca38082805e9bec323473a1407ca3ee8e4afa9aa67878",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "并联预设显示 12V 电源、100Ω/200Ω 电阻和 0.12/0.06/0.18A 读数，元件、编辑工具、状态与简化说明明确。斜线交叉和电池附近折线使回路连接不易逐条核对，属性栏尚未展开数值编辑。可见读数仅证明当前状态，不能据此确认求解验收。"
      }
    },
    {
      "id": "circuit-lab--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "circuit": 10,
          "editor": 9,
          "measurements": 10,
          "presets": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "adbbfd94cd1070e6ddee84401fba0c4f6ebb9b55276803759aefeeb525c9a2cc",
        "screenshotHash": "ec4bbcd7d6b0b069d82d9459720a9a6ac7250a5a2c51e23c462bc27f0f3b210e",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "串联预设展示电池、闭合开关和两只电阻的完整连线，0.04 A、4 V、8 V 及电流箭头可与右侧测量表核对。编辑工具、串并联预设、重置、单位和简化模型说明可见；参数面板尚未选中元件，测量区下部有局部裁切、小字号较密。只确认此图呈现的串联结果，不据此宣称全部电路求解或交互均已验证。"
      }
    },
    {
      "id": "circuit-lab--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 70,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 10,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 9,
          "measurements": 8,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "79f62459a806d382de565dae20187f11df028fe432bc12d31c81a355fb5a8337",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "顶部工具与绿色电流电压标签可辨；回路挤在画布左上，绝大多数画布空置，结果信息主要依靠细小行内文本。"
      }
    },
    {
      "id": "circuit-lab--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 12,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 8,
          "measurements": 9,
          "presets": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33cfda68d7c182d95abca47ef6ee009312bfa01a9bdac058aa4a6b2acf64852c",
        "screenshotHash": "0d6f60793410e3ae31a66d2739aedcc647d30f288ab6dedcb5e822df88d68ade",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "元件和结果表已有电压电流数据；原理图斜线交错、元件标签随旋转倒置，增加阅读负担，主次分区较松散。"
      }
    },
    {
      "id": "circuit-lab--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 69,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 10,
          "readability": 9,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "circuit": 7,
          "editor": 9,
          "measurements": 8,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "ecebf3ba4001871a0f2776e1b9cd14491bc6bce39ef44aef3874876f57bea690",
        "screenshotHash": "83f000ef027d20b62ceff03fc4f67789227148545e9f75ed715c549ca50d7039",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "编辑工具和属性读数清楚，但默认回路缩在大画布中央，主体过小且空白过多，线路标签难辨。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-1-sol-high-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 10,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2fb252aa6e64a88bf2b24bcf70760c6a3ce09feccaefa38daa0a50d4d498325a",
        "screenshotHash": "236118d71cf0fd07274fc7be3bf5e3ecb86a224cd79b0b9b700f779731a4d301",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "浅色原理图、文字标签、节点、属性与0.04A结果分区清楚，编辑预设和重置入口明确；部分元件值仅在侧栏出现。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-1-sol-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6d36025af9ee5b588b18765167d5e41d36c52bf577cd01517a1cbd04bdb543e9",
        "screenshotHash": "0d8fd2f5416f0e7d4712b9bd080444df125559e0fe22ac08bafd4a567419c56d",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "电源、两电阻、开关和连接节点清楚，电压电流贴近元件，左侧参数与预设集中；部分数值对比稍弱。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f158312bf0495f08628b0cf989ad3d10abd1892489b7ff63ab1f1709b6ce1e00",
        "screenshotHash": "9fbdd0e588914ce95d3627c0ea79607f18bbe32e47a82bbfe6728f0f69b26f87",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "浅色原理图、元件属性、预设与下方结果表齐备；数值标记与表格字号偏小，整体结构清楚。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "circuit": 6,
          "editor": 9,
          "measurements": 7,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "74eba78f0850c8e17d40a226521821fc54876f20b4dfd27824c796f789fc325d",
        "screenshotHash": "caa82c3b9a345e4fb29c794b8ed8810c9a40bc8186ac457a4c7d7d61f2925efb",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "元件工具、属性、预设和数值反馈齐全；回路右侧连接不清晰，电流结果与图示不易逐项核对。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-astra-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f89411e1770a34ca80e2d9e88dd5b2f6ecf50fdce64de551597dff4f96d4b47c",
        "screenshotHash": "5b73148ac123c1e3a131de483db44811f6da6e1ebf6d658432d4d6fd46f69264",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "浅绿工作区内有四元件回路与0.04A结果卡，工具与操作说明清楚；元件符号较简化，端点与字母标记稍拥挤。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 89,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "circuit": 6,
          "editor": 9,
          "measurements": 9,
          "presets": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "70b1b0b6ddeaf35dcbc010b2d4d83c49459438474719326c26d70cd026b97a33",
        "screenshotHash": "dcab55709b788cb47968e282561f7380ebfc223def9f62e72c3d612869e67a56",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "截图可辨四类元件，右侧 0.040 A 与底部电压、电流及方向表完整，串并联、重置和简化模型说明清楚。电池左侧 A 端看不到接线，部分导线从卡片边缘折入，难从图形核对闭合回路；该问题主要影响可辨电路项。读数只证明此截图状态，不代表求解验收。"
      }
    },
    {
      "id": "circuit-lab--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "4187cf215d8e1ae9a5ee35504a8fe21b2475e337e7e4f41cadbbdc29b76394ed",
        "screenshotHash": "41a457146f722e0517c8dfff91ee7e99e9bb67285fea2b21eb4ec10c0291030d",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "12V、100Ω、200Ω与开关组成清楚回路，结果表显示0.04A；编辑与预设明确，表格次级字略小。"
      }
    },
    {
      "id": "circuit-lab--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "4a09bbca5db762fbb0c707e3d31d74e29e9fc20006d9030c28f4b0982581d288",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "空网格旁有元件、预设和操作说明，但没有已搭建电路或数值结果；截图只证明初始编辑界面。"
      }
    },
    {
      "id": "circuit-lab--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "cb61307a01f9b16e710e984839d10ab2d4bb9841ab33481acc17b81816e266c0",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "元件、预设、图例和求解入口可见，但网格没有任何元件，结果栏等待操作；当前截图不足以评价电路成果。"
      }
    },
    {
      "id": "circuit-lab--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 60,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 11,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "circuit": 6,
          "editor": 8,
          "measurements": 3,
          "presets": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "6bb0165dbc41b199b98f8cbd05928acaf16d36b9519dc1b6cefc58a6f358768f",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "四个带名称的元件框连成矩形，工具和预设可见；元件缺少清楚原理符号，首屏没有电流电压结果，回路留空较大。"
      }
    },
    {
      "id": "circuit-lab--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 14,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "circuit": 10,
          "editor": 8,
          "measurements": 9,
          "presets": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "f8dd305e66d6499dbe5a5916bccb1a4076fc7d08fbd2d919e306139e7d28e3f6",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "12V 电池、闭合开关与 100Ω/200Ω 电阻形成清楚闭合回路，图示 0.04A 及 4V/8V 和右侧结果表可核对，串并联与重置说明完整。属性区仍是未选中提示，没有展开编辑表单；方向主要依靠结果表 0→1 标记，未见画布方向箭头。回路在画布中只占窄带，下方留空明显，端子及注释较小。读数仅证明此截图状态，不作为全部求解场景通过的证据。"
      }
    },
    {
      "id": "circuit-lab--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 14,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "circuit": 7,
          "editor": 7,
          "measurements": 8,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "fefe3bec62c4fc88f9d538ffe3d0edc94ef7fab58ad11566ad7843e9820c4199",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "可见 12V 电池、100Ω 和 200Ω 电阻及闭合连线，元件旁 0.040A 与表中 12/4/8V 读数具体。四种元件入口、串并联预设和简化模型说明齐备，但属性表单未展开，方向箭头及灯泡状态未展示。回路占画布比例偏小，元件主要以文字矩形表示。只记录此状态，不证明其他电路求解或编辑验收。"
      }
    },
    {
      "id": "circuit-lab--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 14,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 7,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "4ee25706a1bbd067323578db11dd9b712856a90565c0224031d3e82993abd595",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "串联预设可辨 12V 电池、100Ω/200Ω 电阻、端子与闭合曲线连线；表中电流均为 0.0400A，电压为 12/4/8V，方向列具体。添加元件、连线、五种预设和模型说明齐备，属性表单及灯泡未展开；回路集中于画布一条横线，留白较多，不证明其他电路求解。"
      }
    },
    {
      "id": "circuit-lab--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 15,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "circuit": 9,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "c6cd3c5f4f62f985232dd9ae26c11051547a2778eae6b3e205803b53d9fcdf8b",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "回路以颜色和箭头标记电压电流，元件与节点表可见；控制和结果堆在画布下方，长截图文字密集偏小。"
      }
    },
    {
      "id": "circuit-lab--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 9,
          "measurements": 9,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "066592142af6438ac843e17e9405af240232ccae1c38a13172f0ac6c43923ddd",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "元件、连线、结果和说明俱全；弧形导线在元件下交错，符号偏小，读图与结果定位成本较高。"
      }
    },
    {
      "id": "circuit-lab--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 10,
          "measurements": 10,
          "presets": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "31eedd96aae353ea608f3899f47b3dfbe28f1c144b4fef358ed38dd8f742f238",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "工具、节点表、元件表和电路概览丰富；回路被压在大画布左上，表格和说明偏密，画面主体不突出。"
      }
    },
    {
      "id": "circuit-lab--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 12,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "circuit": 7,
          "editor": 9,
          "measurements": 2,
          "presets": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "86b03b822e6e2f05834dd0bb865431d8833bbd8cfaa2a5e6dc6298d374ad4baf",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "三元件回路与编辑工具已显示，但结果区仍写等待求解；画布和内容偏小，下方留白过多，未记录计算结果状态。"
      }
    },
    {
      "id": "circuit-lab--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 69,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 12,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 9
        },
        "taskChecks": {
          "circuit": 8,
          "editor": 8,
          "measurements": 8,
          "presets": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "33e4966a8b9b6da5aedd18996be1cf0471f7f29c1ccad40ef2e167cedc8a0938",
        "screenshotHash": "4de6bf7bc0b149cd24660145250e759d49b75f5388535af81d9d17b3a5114fb0",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "12V串联电路、0.04A与4V/8V标记可见；斜导线、旋转标签和很小的操作说明影响可读性。"
      }
    },
    {
      "id": "circuit-lab--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "c6a1ce57a6d0d3a9cb70ad4856aa297ccf91155ac8aa9b8c67b5a3375e89b66a",
        "screenshotHash": "e53cb2f174efbd4d4486e25736a483867cd0e96708ced10a861d55da9e5fb64d",
        "criteriaHash": "bd67da4445a55506bb30f46c246942d3d83bb7dcb63af97a2513014108035bb4",
        "evidence": "截图显示元件工具和空白网格，未放置电路且未选中元件；这是待操作界面，缺少电路成果证据，不应判成求解失败。"
      }
    },
    {
      "id": "fantasy-map-generator--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "b32ba8424721f823bb258405adda667d5db8b96981d7085a302edb7abdd81f10",
        "screenshotHash": "2e983293ebc9db24edb3eda893de9836e16b63ba3376e90b3b2ab31c6e89e086",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "截图主画布为纯黑，只有种子、海平面和编辑导出侧栏；没有地图也没有明确错误提示，无法据此判断生成成果。"
      }
    },
    {
      "id": "fantasy-map-generator--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 70,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 6,
          "controls": 9,
          "mapStyle": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "99a936a45fbb7036b75f677775726685950d34f43504632ce4a62a0c9908cfbc",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "岛屿立体地形、城镇、水系与图例可见；主体偏小，地形阴影较硬，细小标签和暗色控件可读性一般。"
      }
    },
    {
      "id": "fantasy-map-generator--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 95,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 19,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "terrain": 10,
          "waterways": 9,
          "controls": 10,
          "mapStyle": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3115ca6b83d8db6ea2bbc3bba3d4c6c621be6cb320b31f47d5c35eb6c3181324",
        "screenshotHash": "9a0533c7fe3c1767dc3c563fca8e7abe96fd14d31645db6b8ad63b7a01bf053b",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "海岸、阴影山地、森林、湖泊与河流层次丰富，城镇、方位标和图例清楚，编辑导出与参数面板组织完整。"
      }
    },
    {
      "id": "fantasy-map-generator--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 8,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "ded87061a301530028831cacf0b311da6b009d87c75cc4d8ae7c2af6bfe8878b",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "海岸线、森林、山脉、城镇与蓝色水系丰富，图例和说明清楚；下方留白较多，部分山地细节密集。"
      }
    },
    {
      "id": "fantasy-map-generator--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 8,
          "controls": 10,
          "mapStyle": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "0f8324d9973445eb18dbac1b945e85c05828f667aec1a8bce79b7210cb237974",
        "screenshotHash": "17520309cb745b42afff04b39e5362bd167ac810342bdaf210c72cf171424fd4",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "主岛与山脉森林、水系和城镇层级清晰，生成编辑导出工具齐备；像素纹理偏重，次级文字小。"
      }
    },
    {
      "id": "fantasy-map-generator--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 5,
          "controls": 10,
          "mapStyle": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "ab3c52a8d246014df0b0a83a23173c2a09e477070642570136d35133289a95b8",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "岛屿、图例与编辑控制齐备；陆地被碎水斑点和纹理切割，河流及城镇层级弱，整体更接近噪声地形图。"
      }
    },
    {
      "id": "fantasy-map-generator--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "terrain": 10,
          "waterways": 9,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "9c104d7e5aa0d33e0e311721c3a76e129c37a65079ea9f317846ebbbf2eec601",
        "screenshotHash": "6145709342b5184d46d825d7445b1103c75138f55fbf7cb3bd46736e3111a77a",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "固定默认种子“星海湾”的地图清楚展示海岸、森林、山脉雪线、蓝色水系及多个城镇标签；画笔、种子参数、缩放、导出和图例齐全，纸色背景与符号形成地图表达。水系短而折线化，山脉中央符号密集，局部标签遮挡地貌；静态图不证明河流算法。"
      }
    },
    {
      "id": "fantasy-map-generator--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 9,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "7a9f05312255a2ff8a3258ab454ebc77612d262d55c5bd85a7ee6edf8f66b3f3",
        "screenshotHash": "4cd9bdf1906aec2e018223dc599e4b88a2049f6d5d33f7111c3c9418855a1911",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "固定种子 windward-01 的岛屿以海岸、平原、森林符号和山峰表现地貌，河网、内陆湖及七处城镇标签可辨。海平面、粗糙度、升降画笔、平移、缩放、标签和整图导出控件齐全，纸张配色、指北针和图例统一；支流密集，局部细线与地形明暗有混杂。静态截图不能证明水文下降规则或种子确定性。"
      }
    },
    {
      "id": "fantasy-map-generator--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 51,
        "dimensions": {
          "taskCoverage": 18,
          "composition": 12,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 5
        },
        "taskChecks": {
          "terrain": 5,
          "waterways": 2,
          "controls": 8,
          "mapStyle": 3
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "393993f1afd7e82f85fb760d1f90daf2ffd91b36b812761d1287a31afeaa2cf1",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "基本海陆与森林色块可见，控制含种子和画笔；河流和山脉证据薄弱，城镇文字过大且重叠，缺少手绘细节。"
      }
    },
    {
      "id": "fantasy-map-generator--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 15,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 5,
          "controls": 9,
          "mapStyle": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "05e39cc45357e4558dbe8cbd153818a3b71f140cfd6f473f0d7554ff711b5451",
        "screenshotHash": "8ca0503caf39be66b3fecf5172c17a1ec61047ad79446559e47aee2a942706cd",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "群岛、森林、山地城镇与图例可见；颜色偏淡、水系细碎，地图上下边缘有明显矩形底色区域。"
      }
    },
    {
      "id": "fantasy-map-generator--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 6,
          "controls": 10,
          "mapStyle": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b7371f5918136e6fdc482fcfa6178e5a6cf9d8f7476096fb6ee44f89160799d5",
        "screenshotHash": "4f688ffd44075f25d0391bb4ea057f893d8618b4def175b4d5653f696fcf47bf",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "放大的山脉雪顶、森林、城镇和编辑工具清楚；岛屿边界被画面裁切，难以总览全图，标签细小。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-1-sol-high-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 5,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "9bb4823e382a84551dc3e58078b2e66e843d24dd456d402a195d6174e94718e9",
        "screenshotHash": "a16f32cd24699d907a04c5e57b07dceabc541b0344b048df74335f14b7804847",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "纸感地图、山脉森林、城镇与编辑面板清楚；河流多为规则直线折线，削弱自然水系观感。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-1-sol-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 5,
          "controls": 10,
          "mapStyle": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "fd47927d8dd4068dc91e9a3cef43a639e1ce70447a4afea38c6ca85af79b2e1b",
        "screenshotHash": "27e98a168b921602dd63558b3285907818ce34852144f4c9f45c81dae3df5459",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "海陆分区、山地树木和城镇标签清楚，工具齐全；河流线条机械且直，地图偏平面色块。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 89,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 6,
          "controls": 10,
          "mapStyle": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f158312bf0495f08628b0cf989ad3d10abd1892489b7ff63ab1f1709b6ce1e00",
        "screenshotHash": "df6bfd994219fb37222aa0b1ee2df26850dbca767bea177781ca1f69c3a19c7b",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "纸感岛图、比例尺、方位标、图例和分区工具完整；山地森林清楚，但水系呈规则折线，非自然手绘走势。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 18,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 5,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f8ce8d3368c99d401756fd67cfffd56b316c5bb579944f3acd2c6ecb0f5b088a",
        "screenshotHash": "4a833071316e772e3ec1bfb9b505ea5ce73111d2eb2fadfc74e48396b2d6dc98",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "纸感版式、岛屿层级与工具组织完整；山林和海岸对比较弱，水系细直且不突出，留白略多。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-astra-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 5,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "61b7d4c23bb073bc43516ce3835a1bbe95a12e4c9a21bb9412c4c750cebc3360",
        "screenshotHash": "18ca3870e2928d14b0b1401c437b7294207a30ea2c0d2259168c26c1010ceab8",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "地图与纸色界面统一，海岸森林山脉及城镇明确；水系主要为直线折线，岛屿细节和水文层次有限。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 7,
          "controls": 10,
          "mapStyle": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "7a1e9d6feed8d2d23aeb7ad014c9917d4a39e3f749d0b92e1f659a07d9cce4a5",
        "screenshotHash": "d76bca5f8bb3a9a94c97fd3c70da9e8dc2241a7cf12313ac8731e66c4655af8d",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "海陆、森林、山脉、城镇、河流和小水体均可辨，种子、地形画笔、缩放、图例及导出齐备。中央山地与外围森林偏同心分布，河道多为孤立折线、缺少丰富汇流关系，海岸阶梯与重复符号较明显；浅色小字略难读。静态图不证明水文或种子算法。"
      }
    },
    {
      "id": "fantasy-map-generator--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 5,
          "controls": 10,
          "mapStyle": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d1f504c2ec3f604d3a1b6821507ff8f44da3f6f9b1bc2a8aec1ebfe8faff1c7d",
        "screenshotHash": "426da1e63b5b0e554a2ed5c3fc47eef6cd032bed9daa0c365462020df4bf3bd1",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "浅色纸感与山林城镇图例统一，生成画笔导出清楚；岛屿贴边，河流大多呈规律折线。"
      }
    },
    {
      "id": "fantasy-map-generator--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 10,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 6,
          "controls": 9,
          "mapStyle": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "230d73cbe2a2b996a472a7d8ca14a2b87f7c9fd60d87a0227bad70a6a6b5fac1",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "海岸山地和种子编辑工具可见；地图缩在上半区且下方大块空白，城镇较难辨认，像素表现偏粗。"
      }
    },
    {
      "id": "fantasy-map-generator--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 46,
        "dimensions": {
          "taskCoverage": 16,
          "composition": 10,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 4
        },
        "taskChecks": {
          "terrain": 5,
          "waterways": 1,
          "controls": 8,
          "mapStyle": 2
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "7f1251593e47626224ce4ed71b13d8166ee3384f0d2727c7859c567f54cca2d2",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "生成与编辑工具可见，但地形被横向拉伸成条带，森林山脉仅色块，截图中缺少清楚水系和城镇细节。"
      }
    },
    {
      "id": "fantasy-map-generator--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 63,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 12,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 6
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 6,
          "controls": 9,
          "mapStyle": 4
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "9c1810387f3e7ab6a070760f9a0c3451778d1791d21f423deaf5dd4e86604e23",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "地图包含海岸、森林、雪山与城镇；高亮雪地和橙红色块过强，三角山形密集相压，缺少柔和手绘质感。"
      }
    },
    {
      "id": "fantasy-map-generator--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 16,
          "readability": 10,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 6,
          "waterways": 6,
          "controls": 10,
          "mapStyle": 5
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "39596f2c5de926681311e40cd753654754ee2fce7bc3fa66946bc2355470f7ac",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "固定种子 eldoria 的岛屿、海岸、平原、绿色森林符号、红色城镇及小湖可辨，种子参数、画笔、平移缩放、标签和 PNG 导出入口齐全。当前图缺少明显山脉层次，蓝色河段短且零碎；规则方格和重复三角符号削弱手绘地图表达。城镇标签较小并与森林局部重叠，下方留空较多。图例里的山脉和统计数字不替代地图中实际可见的地貌，也不由静态图证明水文或种子算法。"
      }
    },
    {
      "id": "fantasy-map-generator--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 12,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 6,
          "controls": 10,
          "mapStyle": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "a1bc0a74c8d349150a36ac797ca7acbdd0a2beb27b95f827fb6f0dc83fcc62a1",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "arcadia-01 岛屿有明确海陆、森林、山脉、湖泊和七个城镇，种子、地形参数、笔刷、缩放、标签与导出入口齐备。短河段呈零碎折线，手绘式地貌表达有限；地图只填满框内左上区域，右侧和底部大面积空白，种子小字与海色对比弱。静态图不证明种子复现、地势水文或画笔联动。"
      }
    },
    {
      "id": "fantasy-map-generator--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 74,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 16,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 5,
          "controls": 9,
          "mapStyle": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "97c3be710c125dfdaddfff36de33b33871cbbb57eb15e31183b7f7de4e264913",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "固定种子 20240718 下可辨海洋、海岸、平原、森林、山脉与雪峰，七个城镇标签和九条蓝色水系可见，种子、参数、画笔、缩放和导出入口齐全。河流呈多条笔直纵向细带，山林主要以色块表示，缺少手绘符号与自然水系层次；截图不验证水文算法及编辑联动。"
      }
    },
    {
      "id": "fantasy-map-generator--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 15,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 7,
          "controls": 9,
          "mapStyle": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "131ebb9fb1c01281b2fb250cbd952a2e4980a04b3b383d9e135a219482dfa04b",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "浅色岛屿、海岸纹理、河流与城镇可辨；地图和控制纵向堆叠，文字偏小，海面斑点较抢眼。"
      }
    },
    {
      "id": "fantasy-map-generator--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 74,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 8,
          "waterways": 6,
          "controls": 10,
          "mapStyle": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "2cf7aa7347600e85f75aa3f4717cd0f6860d6533a62b0e5774a22bd24f39a8fb",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "多岛、山地、城镇和编辑参数丰富；岛形较规则圆环化，河流呈长直折线，地图纹理较生硬。"
      }
    },
    {
      "id": "fantasy-map-generator--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 74,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 7,
          "controls": 10,
          "mapStyle": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "c4537e1adc39f3a7df396b4616ac191ce99748ef683ec8def47278b872bfde61",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "地形起伏、水纹、城镇与参数统计丰富；地表形成密集条纹状浮雕，地图识读和手绘气质偏弱。"
      }
    },
    {
      "id": "fantasy-map-generator--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 63,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "terrain": 6,
          "waterways": 5,
          "controls": 9,
          "mapStyle": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "188996109699998e73127eebba4072d2bf1913cdf2e3202034e89c1b8ab16a91",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "小岛、森林与蓝色水线可辨，生成画笔导出齐全；陆地内容单薄，山脉不突出，标签拥挤且主体偏小。"
      }
    },
    {
      "id": "fantasy-map-generator--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 55,
        "dimensions": {
          "taskCoverage": 21,
          "composition": 11,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 6
        },
        "taskChecks": {
          "terrain": 5,
          "waterways": 3,
          "controls": 8,
          "mapStyle": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3760ddfa2b916f3d6d6de4ff28bf276c9d9cdebad9c2ed8cdd89328a0518ccb4",
        "screenshotHash": "ea89a5a35ab84b8d1149d2a7bef05f712546939e329a36fb9aeb687142da822b",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "种子、画笔、缩放和图例可见；地图大面积单色平地，仅少量交叉状水线，山地与城镇表现不足。"
      }
    },
    {
      "id": "fantasy-map-generator--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "terrain": 9,
          "waterways": 7,
          "controls": 9,
          "mapStyle": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "23bc8d4ffe958f1420e12f5a6ff17a17edd2473444de6a8a40c504340deba967",
        "screenshotHash": "ea672b4c21ed9046ee147f885ae18f2639ff5bf4e825a3a7068fb345ce1657df",
        "criteriaHash": "f58ca5b5e17f3a9fdee2de4ee65b07bd5ceaa4c5c5fb403bf99a73ee7e4d8f22",
        "evidence": "海岸、森林、山地、河流和城镇可辨，工具分组明确；地图下缘超出首屏，水系偏短碎。"
      }
    },
    {
      "id": "fluid-simulation--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "9a881bcbb76e449553e51528530021c7adcf920b6e778dad7e62e9d1f5b551b3",
        "screenshotHash": "d6fbb0346aa6c175a427cdc29dc23cb5e25f2b1b15c58c5cebf2a8beb6ef288b",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "整张截图为黑色，没有界面、染料或错误提示；缺少可核对的任务证据，也不能确定空白原因。"
      }
    },
    {
      "id": "fluid-simulation--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "3fe9b00980952c900defe4d637c2d3b59868c6569bbdf35bbec3a067991affb3",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "参数和运行状态已显示，但画布没有可辨染料，提示需拖动注入；当前截图不能支撑流体结果评分。"
      }
    },
    {
      "id": "fluid-simulation--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 9,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "0568d2d4322f94599a3797926e5b79d645c7269cfe24bd3f13f1bafc3de13238",
        "screenshotHash": "ab4c2a78abb970d01c60cdc120a6b2e5e65bb4adc558e8c8d4912416f57437c5",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "多色染料呈连续细卷和混色，颜色、注入、耗散及网格参数分组齐全；画布稍暗，侧栏信息密集。"
      }
    },
    {
      "id": "fluid-simulation--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 16,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 10
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 10,
          "parameters": 9,
          "operation": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "6a5d4f67f00eb2267217905b61df0d32ca8bd116de5d4e25d7e16a12fd8ef49f",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "多色卷曲、边缘涡旋与混色层次清楚；颜色偏暗，控制挤在底部单行，参数标签和说明字号小。"
      }
    },
    {
      "id": "fluid-simulation--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "dye": 10,
          "mixing": 10,
          "parameters": 10,
          "operation": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "beba294a2a08764200449a69d6ce2dd0a16f830f0bb11c9d105840d9256d5dfb",
        "screenshotHash": "5b541b03c442adb08714da865db4c9d4da8d0bf14381e39ad3a1e99c95a77a47",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "多色流体有丰富卷曲、细边和混合层次，参数与运行控制齐备；左侧说明较密，部分染料贴近画布边缘。"
      }
    },
    {
      "id": "fluid-simulation--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "dye": 10,
          "mixing": 9,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "6066ef44a041e3ef5c130115b450343ba00d5384b656abd268115ed98a548f40",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "多色染料填充主要画布并形成复杂卷曲，调色和求解控制丰富；整体偏暗，左栏文字密集，部分形态被边缘裁切。"
      }
    },
    {
      "id": "fluid-simulation--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 10,
          "craft": 13
        },
        "taskChecks": {
          "dye": 10,
          "mixing": 8,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "24154ee2daef90031a83c3ed29bec3136a36bafb98ebf50ca489c4ee84fcce26",
        "screenshotHash": "faa6536d7169603017b299ff9b8ad5648f37a9ef94f37baec31377ae1e822e97",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "拖动注入三种颜色后暂停，画布显示大范围连续卷曲、细丝和颜色接壤，参数面板包含颜色、力度、消散、压力迭代和分辨率，暂停、清空、重置和截图明确。紫色占比高，部分蓝棕区域偏暗且颜色交汇细节不如主涡纹充分。画面及 FPS 文本不证明求解方程或性能。"
      }
    },
    {
      "id": "fluid-simulation--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19-result.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 8,
          "parameters": 10,
          "operation": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "6dba304e5f7c16941742de13c5998cbf3beeae6188e60fd7db349f5e5ccbc800",
        "screenshotHash": "1177eea1c55bb01e496db54de4eb6a865f1a1097095f8baaa967cea6abbafe23",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "实际拖动注入红、绿、蓝染料后暂停，画布中可辨连续卷曲、扩散边缘及多色流态，颜色、力度、耗散、压力迭代、分辨率和暂停清空截图控制均可见。深色布局层级明确；部分染料偏暗、边缘较模糊，多色交汇的细节有限，说明小字对比偏低。FPS 和求解器文字不作为方程正确性或硬件性能证明。"
      }
    },
    {
      "id": "fluid-simulation--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 39,
        "dimensions": {
          "taskCoverage": 15,
          "composition": 11,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 5
        },
        "taskChecks": {
          "dye": 0,
          "mixing": 0,
          "parameters": 8,
          "operation": 7
        },
        "captureState": "blocked",
        "ceiling": 39,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "d8332d2445d5136b2f2f14666c65bc6799bfb746755cefb82eb4e6c80c95c9cc",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "截图明确显示WebGL或所需纹理格式初始化失败，只有控制栏而无流体画面；提示说明环境阻塞，不据此推断算法错误。"
      }
    },
    {
      "id": "fluid-simulation--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 52,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 9,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 4
        },
        "taskChecks": {
          "dye": 4,
          "mixing": 3,
          "parameters": 8,
          "operation": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "90fd52b5b7914e2533b417be61c95feb847b9fd2983430825cf3fddf2a5990fa",
        "screenshotHash": "ac11dcff87b93b7f1990def77037ce47fdb1794911b277c82808667c318f93ef",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "控制和画布已有内容，但染料是粗糙的灰蓝色层块，缺少清楚的彩色流态，画布较小且下半屏空置。"
      }
    },
    {
      "id": "fluid-simulation--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 63,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 12,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 6
        },
        "taskChecks": {
          "dye": 4,
          "mixing": 5,
          "parameters": 9,
          "operation": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "67a177fc1e3379818e0d39c37ca7b54c7aec7fa9f2eb20914cf63b3e91ba0b49",
        "screenshotHash": "47ad89ce62f75315ffce95dd2cd7062f760bbffa1dc3723644c2b669231a2f66",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "参数和暂停清空导出可见，但画面只记录一个很小的模糊光团，没有展示清楚的扩散卷曲与混色层次。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-1-sol-high-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "dye": 8,
          "mixing": 7,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e16cbea32a04c65eb361e89b4cda51b8a80a2419ad526c73f6846a31db2325a2",
        "screenshotHash": "31eec189a892b08477fe5c10862a726278fc0983e4b5b29af5a1ddd2a43fb815",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "紫色染料的卷曲结构清楚，颜色、迭代、分辨率和运行控制分区明确；多色混合未记录，细部略柔。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-1-sol-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 7,
          "parameters": 9,
          "operation": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "9997453394dc1bb3769d63957857a20f7f1ff325a3acb69b69f103fbc284df0e",
        "screenshotHash": "d849ce309f9db6509f9082be5339a334043fb8cc8b8ad6c2540a1ed9fd8f77c3",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "青色染料形成明显卷曲流态，侧栏参数和画布状态清晰；仅一种染料颜色，混色表现未展示。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 94,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 19,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 9,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f158312bf0495f08628b0cf989ad3d10abd1892489b7ff63ab1f1709b6ce1e00",
        "screenshotHash": "61a26b25077bdfd75537a8441bd73bd611cd523031daea0d61b07e1fafdcc973",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "青紫染料有明显卷曲和交汇层次，画布、颜色、求解参数、状态与操作分区完整；局部亮部略白。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 19,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 8,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2803fb67b907497f8c623611dd2c61c8aa3d1b4728b2f28786263d4a4281757e",
        "screenshotHash": "7e8820b2a2c553d98c6d8a2420248706088e80a446195f88fec309e288c288dd",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "多种染料围成卷曲图形，品牌标题、参数、运行反馈和操作说明层级清楚；各色团之间混合较少。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-astra-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "dye": 8,
          "mixing": 7,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "dc7159da53e32c3cdd3f69bce2590dfde58e2462403025b723597b20968403b6",
        "screenshotHash": "139864fc956e3ad5fc4b1cb5bde26b8dbb2255af1029025900f47e31ec0b12f8",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "紫色长涡旋清楚，画布与参数组织完整，暂停清空导出易辨；只展示单色，细节偏柔。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 17,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "dye": 8,
          "mixing": 3,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "957fbe8cca969ed121b64adba219dc14d192c86d0fa7476d10403f26e33c6430",
        "screenshotHash": "17391bb9c54a629c62cd39bb55e5ebbfafec29c1f52cd69d815db7044b38bf70",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "画布已有蓝白染料团、连续拖尾和局部卷曲，五类求解参数及暂停、清空、重置、截图入口齐全。右侧染料大面积亮白饱和，缺少可辨的多色交汇，边缘台阶和条带明显；画面重心偏右。控制面板清楚，但不据 WebGL/FPS 文案证明方程或性能。"
      }
    },
    {
      "id": "fluid-simulation--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "dye": 7,
          "mixing": 6,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "060d5388b7c6772df89a03090e301f63558902e933aa20da9e9f1ee7cfbcc814",
        "screenshotHash": "ee7aea12765bd09e2c200d85ea6ff5014fd3de857d597a734b52a71702a05785",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "紫橙色环形流态与清楚的参数侧栏可见，按钮说明齐全；染料主体偏小且模糊，混色细节有限。"
      }
    },
    {
      "id": "fluid-simulation--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 70,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "dye": 6,
          "mixing": 6,
          "parameters": 9,
          "operation": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "959cc53c6655f7b2e7e9688286eab0e99441997c7b93267b032ca9829ff85489",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "蓝紫色细带呈卷曲形状，求解控制和说明齐全；染料过暗且稀薄，画布留白多，主体层次较弱。"
      }
    },
    {
      "id": "fluid-simulation--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "1da7e144664c81f3f38dc12e0097def6dc505ea452408cbd0a5f44872fe38426",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "画布为空且提示需拖动注入颜色，参数与按钮可见；这是等待输入的截图，尚无流体成果证据。"
      }
    },
    {
      "id": "fluid-simulation--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 56,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 12,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 5
        },
        "taskChecks": {
          "dye": 3,
          "mixing": 5,
          "parameters": 8,
          "operation": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "c0bc3c15c0463adfa7c5ee50d1e44a41ddf00e808473f11847be1d12c9d0da8d",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "工具齐备，但三团染料与黑色背景对比极弱，画布大部分近乎不可辨，成果展示不足。"
      }
    },
    {
      "id": "fluid-simulation--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "dye": 10,
          "mixing": 9,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "40cece19a9d06aa228cdc93dc2b4e9b0d749e6f43edad631fe39f1010c6ff5f9",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "粉紫和青色染料形成连续卷曲、细丝及多层交汇，主体清晰；右上近白色染料局部饱和，混色层次略弱。颜色、力度、消散、压力迭代与分辨率控制，以及暂停、清空、重置、保存 PNG 和就绪状态均展开。画布与面板组织清楚，右侧说明字偏小、下方留白较多。只评价记录的流态和控制表达，不从 WebGL、方程文案或 FPS 读数认定求解正确及性能达标。"
      }
    },
    {
      "id": "fluid-simulation--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 14,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 8
        },
        "taskChecks": {
          "dye": 4,
          "mixing": 2,
          "parameters": 10,
          "operation": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "a191a11d6204f280ac581658efce61c5bd43982d3641d5a883467d58d5acd0c3",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "画布确有橙色染料团与短拖尾，仍属可评价的局部流态，不是空画布。未见连续卷曲、多色交汇和丰富内部层次；下方存在三角形硬边暗区。参数与运行操作齐全，显示运行中和 96×64 网格，但这些文字不能替代流态证据，也不能据此断言环境阻塞、衰减原因或求解正确性。"
      }
    },
    {
      "id": "fluid-simulation--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "dye": 9,
          "mixing": 6,
          "parameters": 10,
          "operation": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "ed81944ec9fb5d2c9074c5e75c9b3eb107a74dc6f061103e12709dc8a83433ea",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "随机泼洒并拖动注入后暂停，可见连续青蓝染料团、卷曲边缘、细流和分叉，参数与暂停、清空、重置、保存入口完整。颜色以浅青为主，混色层次有限，部分团块发灰且边缘模糊，少量窄标签换行；不据此证明求解方程、GPU资源释放或性能。"
      }
    },
    {
      "id": "fluid-simulation--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 69,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "dye": 6,
          "mixing": 7,
          "parameters": 9,
          "operation": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "9771028a50148b0d1e41c24cd4b6712b2157c14fad543c37fe74177a44a2c240",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "画布有青紫色流体形状，参数和控制齐全；大块高光溢白，混色和卷曲层次被掩盖，底部说明细密。"
      }
    },
    {
      "id": "fluid-simulation--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 13,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "dye": 5,
          "mixing": 6,
          "parameters": 9,
          "operation": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "ea063da0888a5b0d188053bbe3b5d53b1471df6f6fff749aa0b8b5fc0bc30f46",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "画布记录数团彩色模糊光斑，参数与运行信息清楚；流动卷曲结构不突出，主体偏小，下方空置较多。"
      }
    },
    {
      "id": "fluid-simulation--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "a2976c286b8191746e3e0468597bdf8992ce256231f06b57a12d2d537e20b7e1",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "运行参数和绿色就绪提示可见，但中央画布没有染料；截图未记录注入后的成果，不能据此判定流体求解失败。"
      }
    },
    {
      "id": "fluid-simulation--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "b092c2ae9d34a7722f978564bff29591c99ffb40217deb861837fb615d173fca",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "截图有参数和运行状态，但主画布全黑，提示等待拖动注入；未记录染料成果，应补结果态证据后评分。"
      }
    },
    {
      "id": "fluid-simulation--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 14,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "dye": 7,
          "mixing": 8,
          "parameters": 8,
          "operation": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "12a551f3809c260cb092de933b7844d93a44684c514eb3cb37865c38e3e182fc",
        "screenshotHash": "72926da1140734a531dfe093fdd8781247720df3d07081798ee2028fc4ea10bb",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "多色染料有延展和卷曲，但接近深色背景，层次难辨；工具集中顶部细行，参数和成果可读性均偏弱。"
      }
    },
    {
      "id": "fluid-simulation--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "dye": 7,
          "mixing": 8,
          "parameters": 9,
          "operation": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7627fe5794ccce6b31585f572f15cb80e99ad5bc4d2c0d2531bda5e298f6d47e",
        "screenshotHash": "449398495867e9d263c70547b64f91c9913471982e5093830296b88a2fce808e",
        "criteriaHash": "eaf58351ff5b576fa2bfbf2366839b5787aa5ba2c5bdba328491020c6d7b321e",
        "evidence": "三种染料卷曲形状可辨，参数状态丰富；整体亮度很低，画布靠下，截图下缘限制了主体展示。"
      }
    },
    {
      "id": "life-diary--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 53,
        "dimensions": {
          "taskCoverage": 20,
          "composition": 9,
          "readability": 11,
          "interactionClarity": 7,
          "craft": 6
        },
        "taskChecks": {
          "diary": 5,
          "ai": 2,
          "assistant": 5,
          "mobile": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "77b6120fca4efe95faf2a820e87fa2a68215ca70239a39aac27f1083b49287f0",
        "screenshotHash": "7f28fe93810b39f454e3a6b4f5d2e921ce9d0f6d76d9cdfc02994d38111cd3bb",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "单台手机首页包含日记、AI、日历入口；主体很小且四周渐变空白过多，实际流程与细节证据有限。"
      }
    },
    {
      "id": "life-diary--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 52,
        "dimensions": {
          "taskCoverage": 17,
          "composition": 9,
          "readability": 11,
          "interactionClarity": 6,
          "craft": 9
        },
        "taskChecks": {
          "diary": 4,
          "ai": 2,
          "assistant": 5,
          "mobile": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "55a46064bbfd9b142187fd79f184faae847d4730a737bdc4463bcb5279bc5ca7",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "首屏主要是规划说明，底部两台手机只显示上半部；原型主体、操作区和流程成果展示不足。"
      }
    },
    {
      "id": "life-diary--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "15d667e8f5c1c2af9a75b056bee8ed08299ae962857337703e8b1661b276366f",
        "screenshotHash": "9e0e42b6353bc0df3aacd072dfe84c507fbc5b31cd0426a35db92d17125d8f78",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "截图只有产品定位、用户画像与功能规划，没有展示手机原型界面；规划不能替代任务要求的UI成果证据。"
      }
    },
    {
      "id": "life-diary--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "diary": 9,
          "ai": 7,
          "assistant": 6,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "03e601f6a96437732d6096e5776fc0dca6369e3e2d6b85d16c0fd9252085a402",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "登录、情绪首页和日记编辑具体，AI对话部分可见；右侧与底部有裁切，完整助手和洞察流程未记录。"
      }
    },
    {
      "id": "life-diary--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "diary": 9,
          "ai": 7,
          "assistant": 8,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f6e4dc34567e4d920e66e829b24880c66c91f3bcb28da4f1337a3ac4be3a3c42",
        "screenshotHash": "aa5782e9334d836cd47ab1c8f187f1c519741d7fb20266d44300c0b1e2949f7e",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "绿色品牌、情绪首页、写日记与AI识别卡清楚，图表和任务可辨；其余助手与回顾流程未直接展开。"
      }
    },
    {
      "id": "life-diary--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 94,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "diary": 10,
          "ai": 10,
          "assistant": 9,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "bf812d42ef75b6be711fce4ed619b13035191d3486cb54d559c387a89f5b074a",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "原图九屏完整呈现打卡、AI倾听、周报、日记、生活助手与习惯；信息层级和组件一致，少量辅助字对比较低。"
      }
    },
    {
      "id": "life-diary--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 9,
          "ai": 9,
          "assistant": 7,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "7e3ff054a13e83f9ea3c5e52f67454d4f48c852a286b7ad403939b336f61c95d",
        "screenshotHash": "c472fe78139c48cd92369f4ff94ea4535204f2839823c2d1ec41706856dd7454",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "完整长图可辨欢迎、首页、情绪打卡、AI 对话、日记列表/详情、洞察、陪伴花园和个人中心九屏；AI 对话含具体回应与呼吸建议，习惯、日记回顾及摄影素材完整，绿色/奶油色组件一致。洞察趋势卡有坐标文字但曲线区域空白，部分屏幕底部内容被导航裁切，辅助说明字小。仅评价静态产品原型。"
      }
    },
    {
      "id": "life-diary--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "diary": 10,
          "ai": 9,
          "assistant": 9,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "c114dd5100fc9d55478a5ee0fb07d216c71a57d87432b05232cd0a221619a8b7",
        "screenshotHash": "ba49e1ce91f16bc653fec85add3ed12e1360ed663eb4a921896ccc66df98d911",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "长图完整展开今日、情绪打卡、写日记、AI 陪伴、情绪回顾、生活节奏和我的七个独立手机界面。情绪选项、正文与照片、具体对话、趋势图和习惯清单形成连贯流程，奶油色与鼠尾草绿组件一致；部分次级标签和浅灰说明对比偏弱，手机内部仍有未展开的滚动内容。只评价原型呈现，不证明真实 AI 或数据持久化。"
      }
    },
    {
      "id": "life-diary--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 14,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 10
        },
        "taskChecks": {
          "diary": 6,
          "ai": 3,
          "assistant": 5,
          "mobile": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "2ccf901f579d6eaf5cca66120f4b25f00dccd8204c012ffc63bee952030238dd",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "启动、引导和首页成形，第四个记录页被右边界裁切；前两屏主要是品牌引导，AI与回顾流程证据有限。"
      }
    },
    {
      "id": "life-diary--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "diary": 10,
          "ai": 7,
          "assistant": 7,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "936c2347da88e22df028e3760c2ba5e66f5ecf56c6fdb869b8434963fe969e80",
        "screenshotHash": "20c4d2c9f661ac3fe3eb446199a355798bb835759c4741efaf8e39a7d0f9cf99",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "情绪首页、图文记录和日历回顾三屏完整，操作入口清楚；AI仅以分析卡体现，生活助手流程未充分展开。"
      }
    },
    {
      "id": "life-diary--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "diary": 8,
          "ai": 9,
          "assistant": 7,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "b70be8112e445ab5d0049483536ff8a354b47148afd4f217267fa33f3976cdb4",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "三台手机展示AI对话、日记详情和情绪图表；结构一致，聊天与统计清楚，首页与生活助手流程未在当前截图完整展示。"
      }
    },
    {
      "id": "life-diary--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "diary": 9,
          "ai": 8,
          "assistant": 7,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "77b6120fca4efe95faf2a820e87fa2a68215ca70239a39aac27f1083b49287f0",
        "screenshotHash": "94ddf4fe4ca26e9fc486a74c241163b410236e9b794cfe388876f9c75e4c6a95",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "日记、AI回信和回顾有成熟的深浅配色与清楚层级；横向展板两侧手机被裁切，完整页面总览不足。"
      }
    },
    {
      "id": "life-diary--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 9,
          "ai": 9,
          "assistant": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2efde7d43efc2ea7af9556b474aa1bbe835b2c77b747d54207fb8e8fccc9a1a4",
        "screenshotHash": "8816fa8127e6dbcaf545b57e05d1401841f5f75fc97c45df4efeba55ee17be12",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "原图十二屏覆盖引导、打卡、编辑、AI、日历、洞察、计划与隐私；组件统一，部分辅助字偏淡，表单留白较多。"
      }
    },
    {
      "id": "life-diary--gpt-6-1-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "diary": 9,
          "ai": 4,
          "assistant": 7,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d214cf12705b422d8cf4e27a027aefafae7e4cf99622f8c956f5ac48fe4610c5",
        "screenshotHash": "a724620727f71fadf3adc80c83dae9a439602e35c91d62e03f8eb5b7c157643a",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "欢迎、情绪首页和编辑页有完整视觉层级，绿色按钮与纸色主题统一；AI和生活回顾主要停留在入口。"
      }
    },
    {
      "id": "life-diary--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 74,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "diary": 8,
          "ai": 4,
          "assistant": 7,
          "mobile": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d992e2392ba6672bdf3a3ccb8d5b25606861b26df56d29473ec5c18fea55b755",
        "screenshotHash": "cab9798f7b5557586cf99f8de79d99a9ae9471431ce846c838aa6cbb5563ff22",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "摄影引导、今日情绪和日记编辑视觉统一；截图只展示前三屏且底部截断，AI陪伴和洞察未直接展开。"
      }
    },
    {
      "id": "life-diary--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 8,
          "ai": 9,
          "assistant": 9,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "b530abac3bf8f915d37c0d35e3fe3dd7c25d4614667c784f13ffd4edf21ced5a",
        "screenshotHash": "be270147765ad013b21355f648c7ad24ae506520408f9bcf961cf90c28d0c1c3",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "七屏展开情绪签到、写日记、陪伴对话、回顾、趋势、计划与设置；陪伴回应和生活计划有具体内容。日记输入仍为空，时间线显示尚无日记，未展示已保存记录；首页和洞察部分内容贴近底栏，浅灰辅助字对比偏低。演示 AI 回复按原型内容评价，不据此判断后端。"
      }
    },
    {
      "id": "life-diary--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "diary": 9,
          "ai": 4,
          "assistant": 7,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7d59398d186b0bfec835eca245cc1e90aa2ee28d21afadd41d8d860c59eb32b9",
        "screenshotHash": "2f407ed9f84c7902705367ed9fab95a3dcae27fa085c4f0bfc5a0880e21a55f1",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "首页情绪打卡和日记编辑清楚，摄影与绿色主题协调；仅前三屏可见，底部内容裁切，完整流程未记录。"
      }
    },
    {
      "id": "life-diary--gpt-6-luna-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 23,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 5,
          "ai": 3,
          "assistant": 6,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "e720526c31b0ef32088b4110e89be1e593c1eaaf467c33e14d1b8c7a293b52bc",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "单台手机首页制作细致，旁有用户路径与产品说明；日记编辑、AI对话和回顾仍以文字规划为主。"
      }
    },
    {
      "id": "life-diary--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 10,
          "ai": 8,
          "assistant": 8,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "d391f6eef9a0d3701df69cb1f891a477e632cd48fbe56f855d18a0a6b2872e3e",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "首页、日记编辑和情绪趋势三屏完整，AI聊天部分入镜；绿色组件一致，右侧裁切限制了全套页面总览。"
      }
    },
    {
      "id": "life-diary--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "diary": 4,
          "ai": 3,
          "assistant": 6,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "8880c189135e8efeb10f7bd25ac0d59713041afab04831958efcb8062867dee0",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "启动和首页两屏精致，情绪及今日安排清楚；记录、AI对话、洞察与设置未在当前截图直接展示。"
      }
    },
    {
      "id": "life-diary--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 14,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "diary": 7,
          "ai": 4,
          "assistant": 5,
          "mobile": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "1b77fde1eb80ccb5006249d3f4f94289d8381150ace602096c182a6b83eb71fd",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "首页、情绪日记和统计三屏可辨，基本操作清楚；大面积空白、简单图标和简短AI建议使原型细节不足。"
      }
    },
    {
      "id": "life-diary--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "diary": 9,
          "ai": 7,
          "assistant": 8,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "00388f20c15d2146ab570eb10e3623f6efa5d8cf001a29c7ef6bf48f2fa81075",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "登录、情绪图表和图文编辑三屏清楚，编辑页有AI整理入口；展板规划文字占比偏高，其他流程未展开。"
      }
    },
    {
      "id": "life-diary--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 12
        },
        "taskChecks": {
          "diary": 10,
          "ai": 5,
          "assistant": 4,
          "mobile": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "0f5bab1a801bcc1378ec21ba4403135fb8bc633a2d33e5d716740cdee9fbda4c",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "今日概览、情绪记录和具体日记时间线三屏完整可辨，照片、情绪标签及记录/保存入口清楚；第四张趋势页只露出均分、局部图表和被截断的洞察文字。AI 仅有简短摘要与标签，未展示完整陪伴对话；生活计划、习惯及个人管理处于画外，不能按顶部七页声明补分。紫色卡片风格统一，次级文字偏浅；日记时间线底栏突出趋势，当前页标识有歧义。截图未展开的页面不等于源码缺失。"
      }
    },
    {
      "id": "life-diary--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "diary": 9,
          "ai": 10,
          "assistant": 7,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "66914b3fc190949420bdefdbaca1e143992f439c769f0c1f279d29eda85c85ff",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "六个手机框展示日记概览、情绪记录、具体 AI 对话及行动建议、周报时间线、统计设置和速记。周报的情绪曲线区域只有星期标签，没有可辨曲线；年度色块、成就与提醒可见，但没有独立习惯清单或计划页面。能量条旁有缺字样方框，次级文字偏浅，速记屏下部空白明显。只评价原型展示，不验证 AI、存储或异步逻辑。"
      }
    },
    {
      "id": "life-diary--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "diary": 9,
          "ai": 9,
          "assistant": 7,
          "mobile": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "7aed61af67974dc92f69451a2d9b8633cce5aa6b6c547d9ed33df686422c74f2",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "长图展示今日概览、情绪记录、日记详情、具体 AI 陪伴对话、周报与个人中心六个独立手机界面，情绪与日记内容具体，紫白组件和导航一致。周报趋势区域大面积空白，生活助手主要表现为回顾和设置，保存按钮被底栏部分遮挡，灰色小字对比偏低；不宣称已有真实 AI 服务。"
      }
    },
    {
      "id": "life-diary--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 14,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "diary": 6,
          "ai": 6,
          "assistant": 7,
          "mobile": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "00682e4b41a83ce560e7a5c33de0b3c27d942a6d657c751f069536181fd5d93a",
        "screenshotHash": "d1be41314a8c47be61feb027343fa2149903b2911113e243d3facaacd5ada007",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "引导与首页的情绪和AI关怀卡有清楚层级；只有两屏且底部截断，编辑和回顾页面未直接出现。"
      }
    },
    {
      "id": "life-diary--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 89,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 10,
          "ai": 10,
          "assistant": 8,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "229055fb813c02577a0464b5da751e16e632aaf694d74b8b6786aa38793118bf",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "首页、AI对话与图文日记形成明确主流程，内容具体、配色统一；手机底部裁切，回顾及设置未展开。"
      }
    },
    {
      "id": "life-diary--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "diary": 6,
          "ai": 10,
          "assistant": 6,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "b5f8a6403e1e33a720315bf79121bdd96f788971e9e22041e127ad7084792696",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "AI陪伴、呼吸与首页情绪设计充分；横向裁切和部分紫底小字影响阅读，日记编辑和生活计划未充分展示。"
      }
    },
    {
      "id": "life-diary--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 9,
          "ai": 5,
          "assistant": 8,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "623ff3a8d31687ddb6d06fa600626b647a07307e67ab8c5996fb05c8af038018",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "登录、今日任务和日记编辑三屏完整，情绪及生活建议清楚；AI对话和回顾页面尚未在截图中展开。"
      }
    },
    {
      "id": "life-diary--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "diary": 9,
          "ai": 8,
          "assistant": 8,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "392a28d27bbed4218066b26ee2b76e9ff353e84bc63213280c61907cf0e8a8c0",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "启动、首页、日记与部分AI对话清楚，生活建议具体；右侧聊天被裁切，完整页面总览不足。"
      }
    },
    {
      "id": "life-diary--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "diary": 10,
          "ai": 10,
          "assistant": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "7a452332fda9bb3ff3829308eeb6e8348075484245a1a423b17f65e473084bb8",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "原图十屏覆盖打卡、图文日记、AI、日历、洞察、助手和个人页；层级成熟，少量图片区使用简化渐变，辅助信息略密。"
      }
    },
    {
      "id": "life-diary--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "diary": 9,
          "ai": 9,
          "assistant": 8,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "bf4ade16ee81eb948a03c53a61ddef1d40a64a13e13976edb665a446876aebba",
        "screenshotHash": "e892bc3d01801a4c5956234a2d021583691df1151f917bb640ec416734ede766",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "首页任务、情绪记录与AI聊天连贯，暖色按钮和摄影统一；左右边缘裁切手机，完整回顾流程未入镜。"
      }
    },
    {
      "id": "life-diary--unknown-unknown-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 23,
          "composition": 13,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "diary": 8,
          "ai": 3,
          "assistant": 5,
          "mobile": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "2f561147b6aeeb883d2c67c7f81921fbbc4a88b27c162fae17fc0c04df9872a9",
        "screenshotHash": "69f5eaeaacd92f9aa7984b692f373dde7b15bb6ebd596e0c9e026982b20dfb8b",
        "criteriaHash": "dea35f75ebcda1f701212cd4bc5533662b205df39966eec7329c6d1887028128",
        "evidence": "启动、首页和情绪记录已出现，但下一排仅露标题；手机尺寸与组件较简单，AI及生活助手的具体页面证据较少。"
      }
    },
    {
      "id": "meditation--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 47,
        "dimensions": {
          "taskCoverage": 12,
          "composition": 13,
          "readability": 11,
          "interactionClarity": 6,
          "craft": 5
        },
        "taskChecks": {
          "discovery": 6,
          "practice": 0,
          "support": 5,
          "ios": 1
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "db6ecbb34ed8ac6ed792b40cb0a7f4d981f866677de7c9bbc109e0e2f793c0eb",
        "screenshotHash": "9a1856010986ce78993ae0f61bb57e1b385463cf193da954ed9eb7f54f3c802b",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "有冥想课程和进度等内容，但以宽版网页列表呈现，缺少iOS移动端原型及实际练习页面的视觉证据。"
      }
    },
    {
      "id": "meditation--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 23,
          "composition": 12,
          "readability": 12,
          "interactionClarity": 7,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 2,
          "support": 4,
          "ios": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "08a633a1f1cd3c0a55a233606246e8f7009c48093a768d071999640a32fb74d2",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "首屏大量产品说明，底部仅显示首页和发现上半部；播放器、练习结果与完整手机界面未记录。"
      }
    },
    {
      "id": "meditation--claude-opus-5-5-max-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "meditation--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 4,
          "support": 5,
          "ios": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "68bb8ac65c9e9856cf5b96d68b92d0c6efa4a3e747ecd560c107f3af6c68815f",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "引导、推荐和探索分类丰富，播放器仅部分入镜；展板较拥挤且两侧裁切，完整流程展示受限。"
      }
    },
    {
      "id": "meditation--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 10,
          "support": 5,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a5de6f9118ec1b8a89d0917ac26c05c8627813056f2ab3e767d915114fce30b2",
        "screenshotHash": "85b53b18161a804f7bd525ae68d85e79edb8565a63d5655736f219c10b9131ae",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "启动、发现与播放器三屏一致，计时、播放进度与操作可辨；睡眠反馈和个人统计未直接展示。"
      }
    },
    {
      "id": "meditation--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 94,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 10,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "31122e326f515c49b94d958f05cabd502225468c1df6f38d2e7cef7cd14c36c1",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "原图八屏覆盖欢迎、课程、播放器、呼吸、睡眠、统计和个人页；深浅组件协调，操作清楚，部分说明文字偏淡。"
      }
    },
    {
      "id": "meditation--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 8,
          "ios": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "c4076827370f0e8a6596ffbcb25eac72393bd669ea3a777a6ce934d97c228c3e",
        "screenshotHash": "665e07f4506aa8017c9bb122c2d48f4abfad58abca02f7ad9ae8391c47a08d78",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "欢迎、今日、发现、播放器、呼吸练习、睡眠、进度及个人设置八屏齐全；摄影课程卡、倒计时光圈、播放进度、环境声与睡前程序具体，雾紫深色练习屏和浅色发现屏一致。每周练习时长图表只有坐标，局部底部内容与固定导航重叠，细说明字小；未把原型读数视为真实播放或计时测试。"
      }
    },
    {
      "id": "meditation--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 9,
          "ios": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "86ef4b5baaafd0ca867dbcd7717f57ae3e8f75092ea29b101001276a8300e4eb",
        "screenshotHash": "29814197635a05342541c5155a73ea9f8c367815b0d9514e5ae762a530c89538",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "七屏覆盖欢迎、今日推荐、播放、呼吸、睡眠、探索和个人进度，森林及山景照片、课程时长、播放器进度与呼吸相位均有具体内容；独立手机边界、底栏与紫青色组件统一。深蓝背景上的部分次级标签、睡眠标题和说明对比偏低，长图中小字阅读成本较高。计时与按钮的可见状态不证明真实音频、账户或订阅服务。"
      }
    },
    {
      "id": "meditation--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "8f87d62ab5220df021c55272a3ef26321ee939f6082d91889a69724a6135591d",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "首页、课程、播放清楚，呼吸训练部分可见；右侧裁切、上下留白偏多，统计和个人页未展开。"
      }
    },
    {
      "id": "meditation--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 5,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e96a1001449464675ce1e92995b0a7baff61599a215c8075d601690f524ef119",
        "screenshotHash": "dc5247159ce22013b5cf49c0f6212c11e7431ace2e6560c01b63bdf55102bc21",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "首页、课程与摄影播放器三屏清楚，进度和播放按钮易辨；睡眠、反馈和个人数据尚未在截图展开。"
      }
    },
    {
      "id": "meditation--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 10,
          "support": 9,
          "ios": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "04e611904da6e19abef7fb1048a43b5830cbc95a673f94095ee1e4bf5fdb5bf5",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "播放、呼吸、自然声混音与个人数据可见；展板两端手机被裁切，部分图标混用和深色小字影响一致性。"
      }
    },
    {
      "id": "meditation--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 9,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "db6ecbb34ed8ac6ed792b40cb0a7f4d981f866677de7c9bbc109e0e2f793c0eb",
        "screenshotHash": "364c9fcc1c940e2c34b5d5a185034be483b18b3988b660f9a7e03d6cc9a5b558",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "欢迎、首页、播放器和数据睡眠屏层级成熟，绿色与金色克制统一；左右手机被部分裁切，完整页面边界未全入镜。"
      }
    },
    {
      "id": "meditation--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 10,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "8fb186aea48d9f70ee3c0539df23d536110f171b0ba8ae2687102e0ca72296dc",
        "screenshotHash": "f7a46ee23d2e046be6cf3f49e9a965835030d1b7f5486a39b9c226e3a156d3a6",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "原图十一屏覆盖目标、课程、播放、呼吸、睡眠、收藏、反馈与设置；组件统一，留白偏多，辅助字较淡。"
      }
    },
    {
      "id": "meditation--gpt-6-1-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 3,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5c0b5df4cae31487ad3473837e68f4b4d74495704724c7aafbd001e7787570ba",
        "screenshotHash": "6f217b075f21ba14e4c6629bcdaf7444008453e6470318cb4e50d92b174a0500",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "森林主题欢迎、今日与课程屏统一清楚；播放器和睡眠等后续流程未直接展示，截图下缘截断导航。"
      }
    },
    {
      "id": "meditation--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 3,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b6a4327aaa26a78d25cb8f5b0ddcdd0f9a1ad5258f838cd5c389f613c59eb229",
        "screenshotHash": "eee160175e7bfc052392229e9903477538ea13e6691416454558ffd5b20eb916",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "摄影欢迎、推荐和课程列表有统一节奏；截图仅记录入口与发现流程，实际练习和回顾未展开。"
      }
    },
    {
      "id": "meditation--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 89,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 10,
          "support": 9,
          "ios": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "c0ad67669b9707cc28e6a9c64ae3f1ae516bf4952f75c29f223cf6a36b3052da",
        "screenshotHash": "c2bc9dd0a1ac58e16b0cf4c4c7fd5fa91325bac016b25ab9bedacd927004e3d1",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "七屏完整展示推荐、探索、课程、播放器、呼吸、睡眠和个人记录，播放与呼吸控件具体，摄影素材和布局统一。截图中的播放器为 00:00、呼吸为准备态，练习与收藏为零记录，未展开完成反馈；辅助文字对比偏弱，彩色播放表情与线性图标混用。不能从截图证明计时或音频运行。"
      }
    },
    {
      "id": "meditation--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 3,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "92e50216fa617c2f0e30dcdc6650a52ed4446cc86edfde52789e149133a86ddf",
        "screenshotHash": "c649fc140f6d2d765aff6667a44ddf7c6c77dc25becdc8da74fef425e93a44c8",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "浅色欢迎、今日与课程探索三屏精致；播放、呼吸和练习完成状态未直接出现，底部内容被截图截断。"
      }
    },
    {
      "id": "meditation--gpt-6-luna-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 23,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 8,
          "practice": 2,
          "support": 4,
          "ios": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "644db5cf1c95d86c44229eabbf4635e36338484bffa0c23a44694246a93ceab8",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "单台首页手机与课程卡制作细致，旁有页面目录；播放与回顾仅有入口或设计说明，整套原型证据有限。"
      }
    },
    {
      "id": "meditation--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 6,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "738de9b636702da7d61de106bad1faa8ba9e4bbde325c90816093a6b60a18d58",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "今日、探索与呼吸播放清楚，绿色主题与摄影协调；睡眠页仅部分入镜，底部与右侧有裁切。"
      }
    },
    {
      "id": "meditation--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 2,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "b44f61a397a6742954a75caf3431098e2ec05eea819711921bdaf91ca2246a20",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "启动和今日首页两屏完整，分类与推荐可辨；具体练习和回顾页面未入镜，启动屏占比偏大。"
      }
    },
    {
      "id": "meditation--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "discovery": 7,
          "practice": 8,
          "support": 2,
          "ios": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "38b517fa8280251895a9520883d1c2e1ce4459c899170d9fc7b74c475234e548",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "首页、播放与课程列表可辨，主按钮清楚；缺少摄影内容，组件和信息较简略，完整辅助流程未展示。"
      }
    },
    {
      "id": "meditation--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 10,
          "support": 4,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "ba86c60809ec341a08e152f7e81c8e50de342e51f3d05cbf004dac038c1ece44",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "欢迎偏好、推荐和练习播放三屏完整，呼吸与进度控件明确；睡眠统计等辅助流程未直接展开。"
      }
    },
    {
      "id": "meditation--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 9,
          "support": 4,
          "ios": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "66f418697f82068b3fba9ed95a0f9a56c541f189095e53db53527a0c3324606b",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "首页推荐、场景库和播放器三屏完整，课程照片、名称、时长、进度及暂停操作具体；右侧仅局部显示呼吸页。首页三个累计统计可评价持续使用线索，但没有展开睡眠、设置或完成反馈，顶部七页文案不算页面证据。深色卡片与薄荷绿按钮统一，部分辅助字及手机边界对比偏弱，办公照片、表情导航和播放器素材语汇略杂。静态播放器进度不能证明音频、计时或呼吸交互运行。"
      }
    },
    {
      "id": "meditation--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 9,
          "support": 9,
          "ios": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "3f08ec48780a2d5bbc7d348a4a47b75bba66b91be0427c42e0b519f24418d335",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "八个独立手机屏覆盖引导、首页、播放器、课程库、睡眠、统计、会员与设置；摄影、呼吸节奏、计时和设置控件具体。睡眠屏顶部只有夜空文字与大片暗区，播放器浅字压在亮背景上，辅助文字对比弱，部分图标为缺字样符号，多个屏下部留白大。没有由静态原型推断音频、倒计时和呼吸动画已验证。"
      }
    },
    {
      "id": "meditation--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 9,
          "practice": 9,
          "support": 8,
          "ios": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "a82cd43ba4234727e19545a859f7d4ba1108e0ca0d3fe4b08848dd965b187739",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "长图展示首页、呼吸引导、课程播放器、课程库、睡眠声音与练习记录六屏，摄影、计时进度、播放状态和记录内容具体，深色手机组件一致。首页若干标题与正文在深底上为黑色，课程文字细小，部分内容靠近或被底栏截断；截图不证明播放、计时或导航功能。"
      }
    },
    {
      "id": "meditation--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 66,
        "dimensions": {
          "taskCoverage": 23,
          "composition": 14,
          "readability": 11,
          "interactionClarity": 7,
          "craft": 11
        },
        "taskChecks": {
          "discovery": 8,
          "practice": 2,
          "support": 5,
          "ios": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "fb72708ddb300014587861bc328444818f0a16349b2244adb72f67c1caf93eae",
        "screenshotHash": "f5f8fa5b1c0c48747a3fb03b8c149b18e7ee9506f2798a08ba499e28d352fef5",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "偏好引导与今日推荐有明确主题和层级；仅两屏且底部截断，进行中练习、睡眠与回顾未直接展示。"
      }
    },
    {
      "id": "meditation--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "e26f95bcafc5c9484fd4a030ff8fe982d5c837330b91ac92082240262704e445",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "首页、发现和摄影播放器信息充分，深紫组件统一；底部截断，睡眠与个人回顾流程未直接展示。"
      }
    },
    {
      "id": "meditation--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 5,
          "ios": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "4db4beb5945b64a8da57028cf9ff1c90bf5ed69d0b86e4df6d16a478bf6bccbb",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "摄影首页、探索和圆形封面播放器精致，主要操作清楚；部分图文靠近底边，完整辅助页面未记录。"
      }
    },
    {
      "id": "meditation--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 5,
          "support": 5,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "923efc13a4ea13342a9ea2948e4aac329ccf20345ae8f2d77501c28001af5abb",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "暖色欢迎、推荐课程和课程详情精致，主流程入口清楚；练习进行与结果回顾状态未直接出现。"
      }
    },
    {
      "id": "meditation--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "discovery": 8,
          "practice": 9,
          "support": 5,
          "ios": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "9d63fc2109bfee074184441c55f41ffe96de0eb7fbf1212c75f2130ea19f5c31",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "欢迎、课程首页和呼吸训练可见，第四个睡眠页被裁切；主按钮清楚，部分界面留白较多且视觉细节简化。"
      }
    },
    {
      "id": "meditation--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 10,
          "ios": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "4998e274d9a5930e4cadebf1e08f7e79f92560699a591fa0528e6012f2d89e92",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "原图八屏覆盖目标、课程、播放、结课、混音、统计和会员；主按钮明确，深色小字对比稍弱，课程封面部分较抽象。"
      }
    },
    {
      "id": "meditation--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 9,
          "support": 6,
          "ios": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "43071e772ffbc0d93444cba1805a4ddeb039cca962056afa8832abae91376148",
        "screenshotHash": "01297ba3d06ff760d0fef08a2e7e35a5f73cff596285e529eb36d5808020dc26",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "课程、今日推荐与播放界面清楚，摄影和深紫主题统一；横向超出截图且底部裁切，完整睡眠与统计流程未展开。"
      }
    },
    {
      "id": "meditation--unknown-unknown-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "7fb4c4bd6632e2ad48358bf4bc5ed94b386d548071115b482e62ebdce6a72381",
        "screenshotHash": "6fbc19d354d81cdd9615a5a5ccba1aa906875c03b36a0d330743a35faa7e0b82",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "截图只显示紫色启动页和外部页面切换按钮，没有课程、练习、睡眠等主体原型；不足以评整套冥想UI。"
      }
    },
    {
      "id": "meditation--unknown-unknown-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "discovery": 10,
          "practice": 10,
          "support": 10,
          "ios": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "4d4f82840938a6e04b7fc29afb3ba601bf51955521ae5dbe8b4834d205a13737",
        "screenshotHash": "0546ac8c7082958c4d60bce534794c0a7afe589f172e444debb382ea617b564e",
        "criteriaHash": "42b020e0417f40594bb2a0b9821e3824472b1662b9adf26bd4e05148e9876f41",
        "evidence": "五屏总览含课程、播放、睡眠和统计，深浅绿色组件一致；手机被整体缩小，细小标签阅读较费力。"
      }
    },
    {
      "id": "neo-gothic-tower-city--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "891306056432fc9c8486f975109fe18dade777ea52523456b0c8db303455f11c",
        "screenshotHash": "af905520e208433d187360db3c7b8dd5ebdd7cbfbb9e01d461c0501d43942153",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "截图主区域全黑，仅有标题和少量界面线条；没有可辨城市或错误提示，无法有依据地评价城市成果。"
      }
    },
    {
      "id": "neo-gothic-tower-city--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 54,
        "dimensions": {
          "taskCoverage": 18,
          "composition": 12,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 6
        },
        "taskChecks": {
          "gothicForm": 4,
          "cityLayout": 6,
          "architecture": 3,
          "context": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "8ec4a3ee0d8e33701fd0d6986a1e78b5a84287bea825e133a80f282a154da830",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "建筑群和暖色窗格可见，但多为重复方楼与普通坡顶，新哥特式细部弱，前景和天空大色块抢占主体。"
      }
    },
    {
      "id": "neo-gothic-tower-city--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 53,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 10,
          "readability": 7,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "gothicForm": 5,
          "cityLayout": 7,
          "architecture": 3,
          "context": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "86150437e8224fc203fb05591b409ba13c66d7e4db0ee4580c507831b6a3a61e",
        "screenshotHash": "d6282fda1721280f7d0b2e913e51fe53f0ccff40fc926e0535912f72a6b8f13a",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "海面倒影与远处连续城市天际线可见；取景距离太远，哥特构件与街区难辨，上半屏天空占比过大。"
      }
    },
    {
      "id": "neo-gothic-tower-city--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 13
        },
        "taskChecks": {
          "gothicForm": 10,
          "cityLayout": 10,
          "architecture": 8,
          "context": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "1f04f3323264c588ef9a3375b58f1970da60fe6b0a69c56ab5e8f230f0001059",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "密集城市与多层尖塔、发光窗饰和黄昏环境有丰富层次；前景房屋部分裁切，辅助字小，装饰模板重复。"
      }
    },
    {
      "id": "neo-gothic-tower-city--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 72,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 15,
          "readability": 9,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "gothicForm": 8,
          "cityLayout": 8,
          "architecture": 7,
          "context": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "dd7a536c36281c9f215e135a4b938d2df8308e63e54fe55ea7adcc245b47859c",
        "screenshotHash": "4a9a7324d562ac1f702f8b371a4ebe09a2b2f9ac9b0546b7539031a522d39155",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "多座尖塔、连接结构与外围道路可见；暗部较重，前景城墙遮挡街区，辅助控制文字细小。"
      }
    },
    {
      "id": "neo-gothic-tower-city--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 62,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 12,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 9
        },
        "taskChecks": {
          "gothicForm": 7,
          "cityLayout": 6,
          "architecture": 6,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "d4d447b557589f673c0ebfda75628b7704ee770651e79591529b3298093ecd2e",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖塔、平台连接和橙色火焰粒子可见；近景塔身遮挡其他建筑，主塔上端被裁切，空间层级较拥挤。"
      }
    },
    {
      "id": "neo-gothic-tower-city--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19-result.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 74,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "gothicForm": 8,
          "cityLayout": 8,
          "architecture": 7,
          "context": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "049d7fcac1cecae6655266699adc00cac13a34e8bf760ed469a0142408061b41",
        "screenshotHash": "3cae9bfdb0db47ba3cb309c786daae5692da9f0a8e790591617c722e843b35c2",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "关闭欢迎层后的场景可辨高尖塔、尖拱窗、玫瑰窗、密集建筑群、街巷运河和火光，底部巡游/漫游操作清楚。两座主体塔顶被画面裁切，场景整体很暗，立面材质与小构件难辨，近景遮挡限制城市总体布局展示；不据图证明真实比例或漫游性能。"
      }
    },
    {
      "id": "neo-gothic-tower-city--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19-result.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 15,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "gothicForm": 9,
          "cityLayout": 7,
          "architecture": 8,
          "context": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "89e2cf0f8afd2c205b355ac49f42721bae4e90fd99e0c420dcd84b7b02ed478c",
        "screenshotHash": "26b91e47d45f044dce4e7ef6198e81fbb8ecf391886dbaff334bcf02424ea1b5",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "缩小后的总览保留完整尖塔轮廓，可辨主教堂、玫瑰窗、飞扶壁、亮窗、环形城墙及海岛瀑布，环视环城和键鼠提示明确。主体更接近围绕教堂的密集建筑组团，街巷与桥梁细节在此视角不够清楚；夜景大面积暗部及上方黑色背景平面降低可读性与场景完整感。不能由比例尺、FPS 或静态画面确认真实测绘比例和漫游性能。"
      }
    },
    {
      "id": "neo-gothic-tower-city--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 40,
        "dimensions": {
          "taskCoverage": 16,
          "composition": 9,
          "readability": 6,
          "interactionClarity": 5,
          "craft": 4
        },
        "taskChecks": {
          "gothicForm": 4,
          "cityLayout": 6,
          "architecture": 3,
          "context": 3
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "e2c1d7e058a6a0dc200099b0c8a41f6ff36ccbf521324ec3271bc2c929a6057d",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "能看到带灯窗的楼群；上部巨大黑色结构和圆形标记占据画面，建筑细节很暗，哥特风格证据较弱。"
      }
    },
    {
      "id": "neo-gothic-tower-city--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 29,
        "dimensions": {
          "taskCoverage": 10,
          "composition": 5,
          "readability": 5,
          "interactionClarity": 6,
          "craft": 3
        },
        "taskChecks": {
          "gothicForm": 3,
          "cityLayout": 2,
          "architecture": 2,
          "context": 3
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "996f0f8dc3529036309746d4539d5c078fe7bec43cf6bb5dfd9bcfbf9c37d6ca",
        "screenshotHash": "8f3461c4c8bae64715037a6facd9c92966990b67efbf910f3ef171bd785532dc",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "当前视角贴近几面黑暗高墙，只有少数窗灯；城市全貌、哥特尖顶和空间关系没有被有效记录。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 47,
        "dimensions": {
          "taskCoverage": 19,
          "composition": 11,
          "readability": 6,
          "interactionClarity": 6,
          "craft": 5
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 5,
          "architecture": 4,
          "context": 4
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "72fbd53ce381aaa6a1b5bf9360c5302636f6bff884a8dfb4904f8ca0a6b83482",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖塔、中央圆窗和灯点可辨；大部分建筑近黑，主要塔顶被截断，无法清楚观察城市空间和立面构件。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 53,
        "dimensions": {
          "taskCoverage": 20,
          "composition": 12,
          "readability": 7,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 5,
          "architecture": 4,
          "context": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "891306056432fc9c8486f975109fe18dade777ea52523456b0c8db303455f11c",
        "screenshotHash": "45e03bd12ff66f7ca288ae74eefe6894a18b35a8b1a26eb721b7e44ef242ef50",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "多座层叠尖塔与平台有体积感；立面几乎无细节，暗部和近景裁切较重，中央提示不易辨认。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "gothicForm": 9,
          "cityLayout": 9,
          "architecture": 7,
          "context": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "fce32793797020aa691c336991a5002f9ac2db8556d67f943f59341d3a0d58d7",
        "screenshotHash": "d812bbe20502520700165296744f56e1bd704802573aa571af812c7b3ce6b0c0",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖顶分层建筑、广场与海岛城市清楚，控制不遮挡主景；立面和楼型重复较多，哥特装饰深度有限。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-1-sol-medium-r01",
      "screenshot": "evidence/desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 17,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "gothicForm": 8,
          "cityLayout": 8,
          "architecture": 6,
          "context": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "4036150e29498a5cce228c4045ad10ff4103ca483c319f772385666af9abb978",
        "screenshotHash": "4b57f4cfc5db482235f26c00499cd88ca843c9168b5e6c394318af2098f7ce2b",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "密集高低尖塔与发光窗格清楚，场景控制明确；建筑模板化、地面较空，海面强条纹削弱环境质感。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 16,
          "readability": 10,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "gothicForm": 8,
          "cityLayout": 8,
          "architecture": 7,
          "context": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a00204c45de1069bb0efc9828763185d6da4c6a7e8837ad749c77e10e248290f",
        "screenshotHash": "ed74c193fe11986fe754e623599633fa51e0936df37b8146e5e3dad77dbe3ee8",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "桥梁、圆窗、尖塔群与水面构成完整岛城，漫游入口清楚；外墙和街巷偏暗，局部楼群较密。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "gothicForm": 7,
          "cityLayout": 8,
          "architecture": 6,
          "context": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "b47c7e398b7bf29e0f405bff4c2ea335897308a75d3dd3022383157ed3344c36",
        "screenshotHash": "7f96aa829ee2500ca060f7e3daed393a9622bf34b66e13837d7e08ab644f78f0",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖顶塔群、拱窗、入口桥、外围步道和路灯形成可辨城市，环游/步行及 WASD 线索明确。楼型与立面重复，窗饰和建筑构件较简化；前排塔楼遮住中部，暗立面对比偏弱，海面规则条纹明显。HUD 比例和 FPS 数字不作为真实比例或性能的评分证据。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "gothicForm": 9,
          "cityLayout": 8,
          "architecture": 7,
          "context": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7adedc0f16f9b95b89b91e92f48cf763e9d11c87e2069945140ce7b1a43318e4",
        "screenshotHash": "fa31166d9e15efb0540f705c26c055c4e8109d44a71901718733202be27853f0",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖塔、分层窗格、围墙和海面形成清楚城市沙盘；建筑模板较重复，海面条纹生硬。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-default-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "gothicForm": 9,
          "cityLayout": 9,
          "architecture": 9,
          "context": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "0858333e8717d95d0c95a32b9a48ded075b8df5d60e5d105e3e7d1185b488033",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "桥梁连接的岛城和多层尖塔有清楚纵深，中央圆窗及建筑层级突出；整体略雾化，部分细小标签较淡。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-high-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 94,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "gothicForm": 10,
          "cityLayout": 10,
          "architecture": 9,
          "context": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "c112a7bfd435aab43dbcd7655d7a6fc8c0f9fd4bf43e4f8690c403d40262e4e6",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "岛城、桥梁、街区和多层尖塔窗饰清楚，雾海与版式协调；小号辅助文本较淡，动态与真实比例不由截图证明。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-luna-max-r03",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 17,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "gothicForm": 8,
          "cityLayout": 9,
          "architecture": 6,
          "context": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "32193ebfc57ea9b1048e59de1ff697873ab38dfb2415995a1f5340bafdaa32b3",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "城市层次、尖顶窗格和连接建筑较丰富；夜景较暗，外墙和街巷细节不够清楚，局部主体贴边。"
      }
    },
    {
      "id": "neo-gothic-tower-city--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 13,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 9
        },
        "taskChecks": {
          "gothicForm": 8,
          "cityLayout": 8,
          "architecture": 6,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "43ff197806eb6ea641d471f92e4e30dc42c8950bf616ab28bdd3e8fe5cfb719b",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "街道纵深与两侧窗格尖塔可辨；近景取景截去建筑上部，阴影压暗街面，标题和建筑相互挤占。"
      }
    },
    {
      "id": "neo-gothic-tower-city--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 52,
        "dimensions": {
          "taskCoverage": 21,
          "composition": 12,
          "readability": 6,
          "interactionClarity": 7,
          "craft": 6
        },
        "taskChecks": {
          "gothicForm": 7,
          "cityLayout": 4,
          "architecture": 5,
          "context": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "879b94c3b521520ae6a207fbc2a0c7f79efbf9872945c68c078821409600b293",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖顶与狭长发光窗有哥特线索；建筑数量和城市内容有限，主体很暗且上部裁切，地面空间空泛。"
      }
    },
    {
      "id": "neo-gothic-tower-city--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 33,
        "dimensions": {
          "taskCoverage": 13,
          "composition": 7,
          "readability": 4,
          "interactionClarity": 5,
          "craft": 4
        },
        "taskChecks": {
          "gothicForm": 4,
          "cityLayout": 4,
          "architecture": 2,
          "context": 3
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "d6839004935892bd54770e26485ea7ccf73075ba6240b0ab1917023f421e6a60",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖塔和粒子仅能勉强辨认，画面严重偏暗，主体被近景塔身占据，立面和城市布局缺少可读证据。"
      }
    },
    {
      "id": "neo-gothic-tower-city--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 58,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 13,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 6
        },
        "taskChecks": {
          "gothicForm": 7,
          "cityLayout": 6,
          "architecture": 5,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "2cfe5209cc7270fcf2b762b92bc3062e07519e8a1183debed933bc4364b0c32c",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "海岛上有高低尖塔和岩石边界；建筑被浅蓝光与雾压平，窗饰和街区层次较弱，天空留白很大。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 56,
        "dimensions": {
          "taskCoverage": 19,
          "composition": 14,
          "readability": 8,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "gothicForm": 4,
          "cityLayout": 6,
          "architecture": 3,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "b7553e75c4c73c83dc05db78a75a29e12c4414f4c9953836e53f394a6fb2f207",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "尖顶塔群、近远建筑与部分平台连接形成可辨 3D 场景，巡航/漫游、速度、视场角和 WASD 线索清楚。主体主要为方形塔身加锥顶和重复矩形发光窗，没有清楚的拱窗、窗饰及哥特构件，街巷组织也较弱。塔身与黑色环境大面积混在一起，底部平台出画，方形粒子、孤立几何块和扁平月亮显得粗糙。HUD 的比例和 FPS 不作为真实比例、性能或失败归因依据；主体仍可辨，因此维持 rated。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 14,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 7,
          "architecture": 5,
          "context": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "fddcb5a3074e05891ba36d92125e090563697e57dd1d7c1b46570d37ced2a5ec",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "截图为塔群夹道的近距离街景：纵深、蓝色塔身、局部尖顶、腰线与橙色竖窗可辨，漫游键位和自动巡游状态明确。完整塔顶、天际线、桥梁和全城布局没有充分入镜，不能按 HUD 声明补足；拱窗和窗饰证据有限。主体可辨，标为局部展示而非证据不足；不由 FPS、比例文字或说明推断性能、真实比例及动画验收。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 12,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 5,
          "architecture": 5,
          "context": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "6da23df9017b56c3f36bb55e3cdcadeb0ff9fb1b83221e2715e3514ed65fbf54",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "日间场景可见中央双塔、尖顶、扶壁状构件、圆窗和周围塔楼，海浪、平台灯柱及漫游键位清楚。外围塔楼孤立于水面，缺少清晰街巷与桥梁联系；窗饰和外墙重复简化，近景塔楼被画框裁切，城市空间与建筑精细度不足。不从 HUD 数字判断真实比例或性能。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "gothicForm": 7,
          "cityLayout": 7,
          "architecture": 4,
          "context": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "c6e6578a8d142bcd883bb2993cfa232aa515fb4d76eb1e0437aee8cf94a257cf",
        "screenshotHash": "d4b6e1b5a85e5c3c3ef18ea6af3329907000fa983d21c72050f0029b6dc411de",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "高低塔楼、岛台和海面有空间层次；立面多为素色方块，亮日与控制面板抢眼，哥特细部有限。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 57,
        "dimensions": {
          "taskCoverage": 19,
          "composition": 12,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 3,
          "architecture": 4,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "3c39a5bf47a9f20ab3d4b6a0a3e3ed9b8446c1988a9896fd9bfb7227dde42068",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "有尖顶塔楼、海面和漫游控制；塔楼数量少且圆盘大幅空置，城市密度和建筑细节不足。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 61,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "gothicForm": 7,
          "cityLayout": 5,
          "architecture": 5,
          "context": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "5e4af8ed581fe33ce1bad1441886b14dc43b8da9acdeea430ae32cee91b08a44",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "细高尖塔与暖窗成组排列，环境控制丰富；楼群紧聚且单一，街区关系弱，周围点阵海面较机械。"
      }
    },
    {
      "id": "neo-gothic-tower-city--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 37,
        "dimensions": {
          "taskCoverage": 14,
          "composition": 8,
          "readability": 5,
          "interactionClarity": 6,
          "craft": 4
        },
        "taskChecks": {
          "gothicForm": 5,
          "cityLayout": 4,
          "architecture": 2,
          "context": 3
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "7705cbd5cbb102f8e97426cb34e3028cabab111deff7646d2020fe90aa0a7d45",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "能辨认尖塔和零散粒子，但建筑大部分沉入暗部，街区和立面细节几乎不可见，主体边界受裁切。"
      }
    },
    {
      "id": "neo-gothic-tower-city--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 34,
        "dimensions": {
          "taskCoverage": 12,
          "composition": 6,
          "readability": 5,
          "interactionClarity": 7,
          "craft": 4
        },
        "taskChecks": {
          "gothicForm": 4,
          "cityLayout": 3,
          "architecture": 2,
          "context": 3
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "f8f250d3fd530618c398104fc6570699d1e95c0b04a0cf48fa38cb86ffcf0dbd",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "近距离塔身和漫游控制可辨，但密集彩色方形粒子遮挡主体，城市和建筑构件缺少清楚展示。"
      }
    },
    {
      "id": "neo-gothic-tower-city--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 58,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 14,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 6,
          "architecture": 4,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5478c18e8b0adf377785d0506e38c40098c7566b14de99640ff6883efc3205b5",
        "screenshotHash": "d0db806c41e7e7bbc853919a7c287a236d9169c986f184ec4661c3f06914e94d",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "圆形平台上多座高塔和窗格可辨；模板重复、建筑细部少，夜景过暗使城市空间层级不清楚。"
      }
    },
    {
      "id": "neo-gothic-tower-city--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 62,
        "dimensions": {
          "taskCoverage": 20,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "gothicForm": 6,
          "cityLayout": 4,
          "architecture": 4,
          "context": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f08c7423329b3e40c664cd94d491f38a5f3fa74a13bf9129589de31d3f89c904",
        "screenshotHash": "9e00f2b2de2b844dc1f46017e8e6780ab20beb50cef6e7c0a57cda3d8fd5a6a4",
        "criteriaHash": "6aa059053a36f782938700cc7f6e46b9cf3bd80bcdcd7a216f9197dd4d762809",
        "evidence": "圆塔、锥顶、城墙与海面可辨；更接近单座简化城堡，缺少城市街区和细致哥特建筑构件。"
      }
    },
    {
      "id": "pathfinding-lab--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "d8822bf061c61c04401d43cbec920d5a32cd551fbf1b673c9446f8e9cc56f889",
        "screenshotHash": "2ae590878bf09d35bc4de6955f5a4ff2f3d1785dcf2c7e56922215fff4365141",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "只有右侧编辑与算法工具，主体区域未显示可辨网格和起终点；截图不足以评价寻路可视化成果。"
      }
    },
    {
      "id": "pathfinding-lab--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "grid": 6,
          "editing": 10,
          "search": 2,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "66fc9416b97939e2bc946ccabed46873483cbfddb54b6827e3dd0f26f993343e",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "算法、编辑模式和状态栏齐全；当前空网格只有起终点，没有搜索结果，下方大块区域未利用。"
      }
    },
    {
      "id": "pathfinding-lab--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 8,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e6eb00e4448a103a75f9e16647bb4228c06b2a15a46cc7a46c8d3e5ebacbc2b3",
        "screenshotHash": "bf97bef973fcf8812f28b8607132472c1a1a25a48d61417f497bb5fa86905e1d",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "加权地图与三种算法步数代价对照表清楚，编辑和规则丰富；主网格当前没有画出最终路径，结果需结合侧表阅读。"
      }
    },
    {
      "id": "pathfinding-lab--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "grid": 9,
          "editing": 10,
          "search": 3,
          "cost": 9
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "b2d6bcea914fe74ab09f032aee6e8bba246811fdf31cf4734f32fa35a2b56ecf",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "障碍地图、编辑按钮、图例和规则完整；状态为未开始，搜索前沿、路径和代价尚未记录。"
      }
    },
    {
      "id": "pathfinding-lab--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "grid": 9,
          "editing": 10,
          "search": 3,
          "cost": 9
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "1a60740201a2c9981cfef48e7c49ac5c99e41147314a73d5c82bdb79703b30dc",
        "screenshotHash": "20d1ffcdf7d98d02b4d3c62be818c4b8b9f854463ba9941aa5f796f4e8c301e9",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "加权预设、算法、编辑模式和图例清楚；网格尚未运行，结果未展开，底部指标部分超出截图。"
      }
    },
    {
      "id": "pathfinding-lab--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 70,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "grid": 6,
          "editing": 10,
          "search": 2,
          "cost": 9
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "40d95ef7880237885cd606e235a664629e4613c243adb81d160cbaaea74f5df3",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "算法、预设、画笔、图例和统计齐备；只有起终点的空网格，未展示搜索过程或结果，下半屏较空。"
      }
    },
    {
      "id": "pathfinding-lab--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 96,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 10,
          "craft": 14
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "993f75aa5472d99206d9375d3bcc295e65fe1d9495ff5eb952543dee52dbfa65",
        "screenshotHash": "e5e88edb9de7ba5a1c0837d923dbc4e3df3ba1eb71ff94ad5d4f49cffcea2bad",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "A* 在预设地图运行后展示起终点、障碍、高代价格、蓝色前沿/访问区域和绕行黄色路径，结果面板明确 33 步、总代价 33；BFS/Dijkstra/A*、编辑、暂停单步、速度、图例及代价规则齐全。网格占据较高空间，结果位于首屏以下，部分浅蓝格差异较轻；单张结果不验证全部算法。"
      }
    },
    {
      "id": "pathfinding-lab--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "grid": 9,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "74fdda0dbb4213eb8ee917167e963d26d413a75f4fe25a6449c58ec7779fd5ce",
        "screenshotHash": "4937a549d41283ab4c0f0dff697f977a0f297e7422e7db392abbacb9043320d7",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "默认加权地图的 A* 结果以粗红路径、青色已访问格和橙色前沿区分状态，起终点、地形代价 5、29 步与总代价 29 清楚对应。三种算法、画笔、单步、速度、清除与四种预设入口齐全，图例和起点不计代价等规则可读；该图未展示障碍格和其他算法运行态。只证明记录的结果状态，不据此概括所有输入下算法正确。"
      }
    },
    {
      "id": "pathfinding-lab--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 62,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "grid": 6,
          "editing": 9,
          "search": 2,
          "cost": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "e694adcb98265c1bee4559a64b8a372908c975c12df6643f8858d695c88a52f6",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "起终点与编辑、算法入口可见；画布较空且网格低对比，没有搜索和路径成果，控制偏小。"
      }
    },
    {
      "id": "pathfinding-lab--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 70,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "grid": 6,
          "editing": 10,
          "search": 2,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d2c732e77597715c24d0958b054572cb77ddd1b3e8329206db5175e5fe47cc5f",
        "screenshotHash": "211553aca956385e04488769278e3131babf05197cfd7bfc698bf861d4185c8a",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "浅色网格、编辑工具和起终点清楚；状态未开始，搜索过程和路径未展示，说明集中底部。"
      }
    },
    {
      "id": "pathfinding-lab--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 12,
          "readability": 9,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "grid": 9,
          "editing": 10,
          "search": 3,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3b28e71d9b7755432ae2a85da428dd04c32cffabe4fb6278626bf010a3d053e4",
        "screenshotHash": "bf2e127d4bb75c91b54837775c012ca7432f42457c20319561ee7bac891e5938",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "加权地形与编辑工具齐全；网格主体偏小，周围大块深色留白，细小结果字和图例较难读。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-1-sol-high-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "c2ba95b878d649bca4eaf5e58c2062c8ced4789607cf05a5cb6fd625050bb84a",
        "screenshotHash": "185826ae1e3d206cc786ad6ff8788c24894d303a75153b01920a5ea2a015f958",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "路径避开代价5区域，前沿和访问状态有清楚图例，步数代价与控制层级完整；细小标签略弱。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-1-sol-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "c33971b0ffb110a1c735b2d6c2076698a28a0dc31b9429ed892a5f6b0f303c62",
        "screenshotHash": "ac8fcb12126832ec94ffedc6fca7c68f94bc1944e8f091c383cbe678f80dbe8a",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "加权地形、访问状态和绕行路径清楚，步数代价及控制齐全；色块对比接近，部分次级文字偏淡。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "f158312bf0495f08628b0cf989ad3d10abd1892489b7ff63ab1f1709b6ce1e00",
        "screenshotHash": "5c646da08153fdd55a2de4e99c89f61d71a4367b56c33d7ec616935b47a5b64b",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "障碍与代价5格清楚，路径绕过高代价区，已访问与前沿区分明确，步数代价和编辑工具分区完整。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 3,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "82d841b78fcece0371ba949ddbcb4f0716f7c0dd37e70337a18576842bea09ca",
        "screenshotHash": "2e6875a22bbe3bb80469c14934170ba537fe6bd7eb2ec3dae13338ced2ef137d",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "障碍和代价5走廊有明确区分，编辑及算法说明完整；尚未运行搜索，没有路径和代价结果状态。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-astra-low-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "0a4ecd78700047342c673704c94ec79771addabce09d42fddfb478ec0f3e0f5d",
        "screenshotHash": "96ae174242c1ab678c30159faeec153c589780c803fc1ba3ce0ca2452aa33139",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "BFS穿过加权格的路径、访问区域与前沿均可辨，步数和代价同时显示；说明小字较密。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 89,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "grid": 8,
          "editing": 9,
          "search": 10,
          "cost": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "480913fa4bfb53704766d7ecb6f290fee0d6a0129da44df840a329b27815caaa",
        "screenshotHash": "f7371da5f31055a886f890d4c4d7116adece01aa3801dd837e72c547f1758bb5",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "截图记录 A* 在标 5 的高代价走廊旁绕行的结果，访问/前沿、最终路径、25 步和代价 25 均清楚，工具、速度、单步与预设齐备。未展示障碍格，BFS/Dijkstra 的规则差异也未展开；搜索色覆盖地形底色后，高代价主要依靠小号 5 辨识。不由该单态证明全部算法正确。"
      }
    },
    {
      "id": "pathfinding-lab--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 3,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e5af35d3c9bc5007968826ec05836b6865aca40811937b2dd38e8e2f5785d5ff",
        "screenshotHash": "5d9961a489165f01690c3fced3c47b99481e2cfaa35d2dbc903dd156b4b31990",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "高代价区域、起终点和搜索控制清楚，图例完整；当前访问数为零、结果为空，未记录算法结果。"
      }
    },
    {
      "id": "pathfinding-lab--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 12,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "grid": 6,
          "editing": 10,
          "search": 2,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "d2667d9a6f05ba98f2da41b7f426ed0b92505ba1bfc521c68bb78ba055f75d50",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "大网格、起终点、算法与结果栏齐全；当前未搜索，网格下方大块留白，控件和说明较细小。"
      }
    },
    {
      "id": "pathfinding-lab--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 50,
        "dimensions": {
          "taskCoverage": 19,
          "composition": 10,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 5
        },
        "taskChecks": {
          "grid": 4,
          "editing": 8,
          "search": 1,
          "cost": 6
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "28b0b986b50b28cd8e31cc11ff31c80d889c2a0a416314616b8056930eb3338b",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "算法与编辑栏存在，但网格横向压扁、起终点呈短条，结果指标为空，图例与操作层级较弱。"
      }
    },
    {
      "id": "pathfinding-lab--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 48,
        "dimensions": {
          "taskCoverage": 17,
          "composition": 9,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 6
        },
        "taskChecks": {
          "grid": 3,
          "editing": 8,
          "search": 1,
          "cost": 5
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "c880addb3cfab599cb26564989877cb88971189c46da7d6fef0910d47cdc7140",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "顶部工具和起点可见，但大网格超出画面、终点未入镜，路径及统计缺少证据，首屏比例失衡。"
      }
    },
    {
      "id": "pathfinding-lab--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "f159c76854345da597d0fac93757db3212750d9e16380813299bbe2e7aed28d2",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "A* 结果态完整显示起终点、障碍和高代价带，前沿、访问区及绿色最终路径层次清楚，右侧记录已完成、33 步与总代价 33。算法、编辑、暂停单步、速度和预设入口，以及代价 1/5、起点不计代价和算法差异说明齐备。网格占比充分，侧栏长、下半区域稍空，完成后按钮仍写暂停，规则小字略密。只证明此地图的可见结果，不把静态路径当作全部算法正确性验收。"
      }
    },
    {
      "id": "pathfinding-lab--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 8,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "bc90d0f5b0af86f99be443b76f634a6ae29d8c1aac45f3dbfa8b7658802b4f41",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "A* 结果态清楚展示灰色障碍、代价 5 地形、起终点、蓝色访问带和橙色直线路径；图例及 28 个访问节点、27 步、总代价 27 与规则说明齐全。前沿节点为零，只有直线路径，不能给搜索展开过程满分。侧栏与主网格组织清楚，底部说明偏小。总分与旧分同为 88，但检查项与构图、精修维度已独立重评；读数不证明所有算法正确。"
      }
    },
    {
      "id": "pathfinding-lab--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "grid": 9,
          "editing": 10,
          "search": 10,
          "cost": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "898587fb33db55c58bfb2937f9eb344d7cf638a83d11d884226717e4e51dc2d4",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "绕行障碍预设运行 BFS 后，起终点、深色墙、已访问区、青色前沿与粉色最终路径可辨，显示 44 步、总代价 44、访问 686 格；算法选择、编辑工具、预设、图例与规则说明齐备。本图未展示高代价地形的搜索结果，已访问与普通格色差较小，右栏底部规则在取景外；不推广为其他算法验收结论。"
      }
    },
    {
      "id": "pathfinding-lab--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "grid": 10,
          "editing": 10,
          "search": 10,
          "cost": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "e212ef1c43e5a4c0df3e57b3de248f9a701e4b99230d73652ccaec0ed3502895",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "复杂障碍与加权格、访问点和绿色最终路径清楚，步数代价和运行控制齐全；下方说明字号偏小。"
      }
    },
    {
      "id": "pathfinding-lab--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 63,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 13,
          "readability": 9,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "grid": 5,
          "editing": 10,
          "search": 2,
          "cost": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "11067311492a01560c848e43c8dd47482ea9b0399893edf796e449e9aed2b457",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "算法和编辑侧栏齐备，但网格障碍非常低对比，起终点未清楚呈现，结果指标为零，主体识读较弱。"
      }
    },
    {
      "id": "pathfinding-lab--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 62,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 10,
          "readability": 9,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "grid": 5,
          "editing": 10,
          "search": 2,
          "cost": 9
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "fde0680f322d413b5edd37d96e218889fa7670949f4d2def8ba8da9d90fd9cfa",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "算法、地图工具和说明丰富；实际网格缩成中央小块，起终点难辨，统计仍为零，主体被说明压缩。"
      }
    },
    {
      "id": "pathfinding-lab--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "grid": 6,
          "editing": 10,
          "search": 2,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "6b0140c26679995d1eaf390e5d692acf9dc7fba1b4118fe0364693a90f0ab787",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "浅色网格、起终点和编辑控制清楚；搜索指标仍为零，结果路径未记录，顶部控件较密。"
      }
    },
    {
      "id": "pathfinding-lab--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "grid": 9,
          "editing": 10,
          "search": 3,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b8d223f96243cb8d612def43b5188ffaee0daa488f37b783ec84874bc951e512",
        "screenshotHash": "ac2564d7f506c7fefcde1d6fc875034798ab4e7a9112f0aee7f25cbdb83c507f",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "障碍、起终点和预设工具清楚，图例完整；尚未搜索，计数与结果为零，说明小字较密。"
      }
    },
    {
      "id": "pathfinding-lab--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 69,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "grid": 6,
          "editing": 10,
          "search": 2,
          "cost": 8
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "60124861ff32f921c92b6160627b013da8fc1e8cd56c59a8ebce802301c684af",
        "screenshotHash": "43545363e2284b24ed7d577e5c55b2dacbfd4b55c00d27ca7c256830e19aa97d",
        "criteriaHash": "99c1f766b6ab9f4e03aa3654c776f593f266af9407750b6c0814f5bcb144256a",
        "evidence": "网格、起终点、算法编辑与指标栏齐备；当前为空地图就绪态，尚未展示地形、搜索前沿或最终路径。"
      }
    },
    {
      "id": "pixel-flow--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "8c05b10fdca701292d6df10c67724bcebd365dfb87d4b8c4ae8212abb471168c",
        "screenshotHash": "f005bf1f58906f0f1fe1953395700b8ca045e872582d743dbec832941bd6a005",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "顶部上传和相机控制可见，状态显示未检测手部、还原为零；主区域没有图片粒子成果，应补结果态截图。"
      }
    },
    {
      "id": "pixel-flow--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 9,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "243fdc3977a3c35e2535f877c0bdc529bd0b1aef4941db77178d0974768684a2",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子场、摄像头占位与多手势说明可见；左栏较密，原图不可辨且没有手部画面，不能验证还原。"
      }
    },
    {
      "id": "pixel-flow--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 12,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "9e912a8d98a0e6d09b460a343946adc2abc3b77c2b13c332545d802ce9785c6a",
        "screenshotHash": "243e05b082ef982a0b25182945cedf2ef5d1426cd7b49a772b344044893ec255",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子数、上传、手势和还原控件丰富；密集高亮散点干扰面板，图片形态和实际手部追踪未展示。"
      }
    },
    {
      "id": "pixel-flow--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "imageParticles": 10,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "8e49336a0950777496a9a1a80d43671604d43107e8ac3f6bc1c8298ccde135c3",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子已组成带文字和山形的可辨图像，上传、采样、打散与相机入口清楚；仍未记录实际手部追踪。"
      }
    },
    {
      "id": "pixel-flow--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "69bd2c5075584040ec3bb4c02029700645d6b77f34b01ce9474854e8eba1761f",
        "screenshotHash": "6831fb1107761b0c13c58ca914cf9a3ad3f058bfc90bd00d4bf91013c71492ac",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "多色散点、上传示例、手势入口和参数完整；面板叠在粒子场上，字小，原图及实际手部追踪未展示。"
      }
    },
    {
      "id": "pixel-flow--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 9,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "fb4d692e0abe8e87acd1daedea03a314fb2a0365272698acb7631580bd611316",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "彩色散点填满画面，上传、相机和还原入口可见；文字面板小，未展示原图和手部追踪结果。"
      }
    },
    {
      "id": "pixel-flow--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 83,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "imageParticles": 10,
          "imageInput": 10,
          "camera": 2,
          "gestures": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "de23220dfe16f1226118bdb2d82445a962858a37758512689d9dd9faab6e176c",
        "screenshotHash": "57903b31b0b194dbe94d05246d1edaf5672d8632a5031370cd8168c169d1d905",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "默认示例的 PIXEL FLOW 图像以彩色粒子形成可辨文字和矩形轮廓，上传、采样、大小、吸引强度及打散/还原控制齐全，状态明确“已模拟开掌”。本次仅点击还原按钮，画面无相机视频或手部关键点，因此相机项只记入口覆盖，手势项按说明与模拟反馈计，不能视为真实手势验证。"
      }
    },
    {
      "id": "pixel-flow--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19-result.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "imageParticles": 4,
          "imageInput": 10,
          "camera": 2,
          "gestures": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "9f9366f957963af79362420f2fe6c096ae5b9afaa5291ea09f7fcc8367568500",
        "screenshotHash": "10568770065fc6dfffedee5c51173cd354926bf6b16d17e7254257ee0949d714",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "按住鼠标吸引后的画布有大面积彩色粒子与局部规则点阵，侧栏上传、采样、范围、力度、重新散开与进度环具体可辨，显示还原度 78%。本图仍无法清楚识别内置 PIXEL FLOW 原图，不能用百分比补足图像重构证据；摄像头区域明确不可用，只有指针回退与手势说明，没有视频或手部关键点。只按粒子场及控件覆盖计分，不宣称真实手势验证。"
      }
    },
    {
      "id": "pixel-flow--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "89cdff3101ba176a7a64b11446ad7595d0e578ee975970f631f2e12c5357c451",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "画面只有上传、相机、重打散和开始提示，主区域未显示图片粒子；不能把等待用户上传判为失败。"
      }
    },
    {
      "id": "pixel-flow--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "a95cbc266617705d16e904ba0797ef01f098420a729179ebe53f1fe0444dcc9e",
        "screenshotHash": "8c03c62a948bd0404e93fb9dc0d4900715201830bba62beb7679d636432bb3a0",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "主区域没有粒子，说明需先上传图片，并记录摄像头不可用后的鼠标替代；无法据此评价图片重构成果。"
      }
    },
    {
      "id": "pixel-flow--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 17,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "imageParticles": 7,
          "imageInput": 9,
          "camera": 4,
          "gestures": 6
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "8b29146097b900fa8dfd8bc81f387761d3f8a50567daf80463ea946e1d4198a6",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "集中彩色粒子云有清楚空间感，底部上传打散还原入口明确；原图轮廓不明，手部画面和识别结果未展示。"
      }
    },
    {
      "id": "pixel-flow--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 6
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cd116b8e4cb3e147397cea8ac231e85e50c3fec67b72a57d4f33a04a9ddf6f2a",
        "screenshotHash": "68056360560df44b762d0cacc453b6d926f7ede263e01d936c02a005a5c807c0",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "清楚的粒子场与输入、摄像头、状态侧栏构成完整工作区；还原为零，原图与手势追踪未展示。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 75,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 17,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a2f322b605d4a21955efd5d1e06e7118f32093be0938e6c2f4ba834982f76966",
        "screenshotHash": "b2496978726ba96bf763d66651a3933368587889e624e9653b84f35f1baab786",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子场、手势说明、上传、状态与相机入口完整；细小文本较淡，截图未记录可辨图片和实际追踪画面。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-1-sol-medium-r01",
      "screenshot": "evidence/desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "imageParticles": 7,
          "imageInput": 10,
          "camera": 4,
          "gestures": 6
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "ca166153767b28fb5d471b0bced4a95b03172db222c77add1eeb84ed8e3bed73",
        "screenshotHash": "b182f7a32a8eb311622d4b13e3f263f9d9c77648e6c3e82eba8e6071f341ef67",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子按颜色形成局部图像层次，上传与手控面板清楚；还未显示可辨完整原图，摄像头区域为空。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a3375e4bfe25f15b19fa83e412a1e595c98b27d10f403d35ffee8c4da94dd95a",
        "screenshotHash": "eb21ec7ee52214924fcac7376f75de90a4e021e8a3be9bd9783b1d935d752e87",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "环形散点、上传、还原、参数与相机分区明确；还原进度为零，截图未包含可辨图片和手部画面。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "imageParticles": 10,
          "imageInput": 10,
          "camera": 2,
          "gestures": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "d796db8dffb85d834c0c8c27d5c1f62b68e9ec97a14429cedfc79548a92f00ea",
        "screenshotHash": "08bf337cece4a30afb753a3196b28a4e4aa9297221d87938165b6032a6d67394",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "山景原图已由粒子重构，可辨山脉、云层与树林，文件名、采样和 100% 进度及还原/打散入口完整。相机只有启动按钮，没有视频区域或手部关键点；手势仅见映射说明，未记录追踪状态。侧栏底部说明超出取景，图像在画布中占比偏小；相机项 2 分、手势项 6 分均按可见证据。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 72,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 9,
          "camera": 4,
          "gestures": 6
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6616570591b47358f1956b09846418eb2efb510083c767639dcae010004a39c9",
        "screenshotHash": "aedd1e5b8527d8a9d25d14f635eea332e543604b398814a75a20a13fe9a0b828",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "散点粒子、上传、采样、摄像头与还原控制齐全；未展示可辨原图或实际手部追踪，不能据星点推断手势还原成功。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-luna-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "307c4d833819191aacc253f6b12e2b5d8405dc7a532ff97330f5f2fcbd5e452f",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "画布、上传、进度、输入状态和步骤说明层级清楚；截图只有散点，摄像头关闭，图片与手势结果未记录。"
      }
    },
    {
      "id": "pixel-flow--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "753a3c6a5b8344fe0c8c13c13301f5f0966a34b066c4f09cd5d5f7b165b8a148",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "上传和摄像头入口齐备，但主画布没有粒子或图片，进度为零并提示等待图片；仅有待输入界面证据。"
      }
    },
    {
      "id": "pixel-flow--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "298b294bef0ac593ea47ef4e67cecf769775316cb16cf6ce7098ecc98847ccc9",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "截图粒子数为零、还原为零、相机未开启，主画布为空；没有可评分的图片粒子化或还原成果。"
      }
    },
    {
      "id": "pixel-flow--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "23fdf20e7dbf1ce25147139468f499b39ba74b8fc421433d7d5e92f085d6ef92",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "界面提示上传图片后生成粒子，当前画布和摄像头区域均为空；待输入状态不足以评价核心成果。"
      }
    },
    {
      "id": "pixel-flow--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 74,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "ad8270e68dd6072708f577a5c99bf70a6cbc6aa2cdb2e267cf4a70963bb9d865",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子场、上传、还原和手势说明齐全；状态为等待粒子、相机未开启，图像重构与追踪结果未展示。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 11
        },
        "taskChecks": {
          "imageParticles": 10,
          "imageInput": 10,
          "camera": 2,
          "gestures": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "ae5bf53c9f7cb793a7cd96b9ca31879f44c5ebc5b4b46af54d6b2feca8bf73bd",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子点阵清楚还原笑脸和条形图案，图像主体可辨；选择图片、示例、采样、速度、力场、打散/还原与 100% 反馈完整。相机框明确摄像头未开启，只有启用入口，没有视频或手部关键点，相机项为 2；底部张开手掌/握拳说明不替代追踪，手势项为 5。中心图和面板不遮挡，次级标签及底部小字偏暗，示例造型较基础。该图支持图像还原状态，不支持真实手势功能已验证的结论。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 12,
          "readability": 11,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "imageParticles": 8,
          "imageInput": 9,
          "camera": 3,
          "gestures": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "dcb994a28f7c33b8aa0b20dee87812da10e58d8dce3f88b15bb7dc314e420e76",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "可见高亮粒子点阵形成圆形与 PIXEL FLOW 图案，侧栏记录还原度 100%；图案放大到视口外，FLOW 底部被裁切，说明面板也覆盖主体。画面偏亮泛白，不能沿用旧评语中偏暗的描述。相机框为空且追踪未启动，顶部捏合还原文案与鼠标替代状态不构成真实手势证据。按局部图像成果评分，相机和手势仅计可见入口、说明与反馈。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot-restoration.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 17,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 8,
          "camera": 2,
          "gestures": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "d5ea74a7a1861f559fabd33767b8c56ebeb7a5057548f4f7ee3a6f339b36096f",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "载入内置示例图后以页面提供的鼠标牵引交互截图，可见彩色粒子从散布变为斜向规则点阵及接近完成的进度条，上传、采样、重置和三种手势说明明确。点阵未清楚还原示例图的圆环与文字，画面仍显示还原中；相机区域黑屏、手势未检测，没有真实视频或关键点证据。不将鼠标替代操作视为手势验证。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 10,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "da2c69819237ce62341f6350f0edca24dac7071403ffdcfdca46eb1104d9ec04",
        "screenshotHash": "09b6643d345c7b4f80ba03b183d731783316278acd4cd1cf7a1c462c47036365",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "彩色粒子、上传参数与手势说明分区齐全；摄像头未开启且还原为零，原始图片和手部效果未记录。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 59,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 6
        },
        "taskChecks": {
          "imageParticles": 4,
          "imageInput": 9,
          "camera": 4,
          "gestures": 5
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "56b7c242f5b5f6e775b841ccff08713ea1295fb78560701d7ad2d68fb2d739d4",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "参数和已载入粒子数可见，但粒子极暗、原图无法辨认，摄像头未启用；成果及追踪证据均弱。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "eb48fab25799c31dfbfde28524dcec8fac5cdfbe283c582339d4234463b0db8a",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "画布明确显示还没有图片，右侧有上传和相机待启动提示；这是初始占位状态，缺少成果评分证据。"
      }
    },
    {
      "id": "pixel-flow--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 56,
        "dimensions": {
          "taskCoverage": 19,
          "composition": 12,
          "readability": 10,
          "interactionClarity": 6,
          "craft": 9
        },
        "taskChecks": {
          "imageParticles": 5,
          "imageInput": 8,
          "camera": 2,
          "gestures": 4
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "3583121ccf09e352dfedb5f4a66132888ad1bca798251070124e6d71d83b458e",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "有彩色景深光点和上传控制；没有可辨原图、摄像头画面或还原结果，光斑过大模糊且文字偏小。"
      }
    },
    {
      "id": "pixel-flow--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 61,
        "dimensions": {
          "taskCoverage": 23,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "imageParticles": 4,
          "imageInput": 9,
          "camera": 4,
          "gestures": 6
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "029bcfb04078a8018bdea35bf16e465cb945a159a0e5073c52245f369c697619",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "截图有粒子计数和相机面板，散点却非常暗，原图不可辨；操作和说明齐备，实际手势结果未记录。"
      }
    },
    {
      "id": "pixel-flow--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 73,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "imageParticles": 8,
          "imageInput": 9,
          "camera": 4,
          "gestures": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "cea7d97985d6fe8c50e5fb424a8d26e6bc0d0d094e8e6e7e105b020e15651d95",
        "screenshotHash": "e930ff2ec464ad7ca008214c09ef133a75d19a8b64145e197a723def4e132606",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "规整彩色粒子矩阵与100%还原状态可见，上传和采样清楚；图片主体识别度有限，页面明确提示相机不可用并使用鼠标替代。"
      }
    },
    {
      "id": "pixel-flow--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "imageParticles": 6,
          "imageInput": 9,
          "camera": 4,
          "gestures": 7
        },
        "captureState": "initial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "179b45c891f5450f946d930803c559b4ac0682d143d9a642d6f91883f6a287d5",
        "screenshotHash": "7207226c5d17817203b8b5b0971dd37e3dbc78a63113e009137e99c208fa2eca",
        "criteriaHash": "b9745213a68e7588df1b0395ab8fa166c67ba11b3caa17cf7f268e06516482a3",
        "evidence": "粒子、上传和手势说明齐备，并明确提示相机未获取后的鼠标替代；图片重构与实际手部画面未记录。"
      }
    },
    {
      "id": "pixel-flow--unknown-unknown-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--claude-haiku-45-default-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--gpt-5-6-luna-max-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--gpt-6-1-sol-max-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--gpt-6-1-sol-medium-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--gpt-6-luna-max-r02",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--gpt-6-sol-medium-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--minimax-m3-1-flash-preview-max-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--minimax-m3-max-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "stock-watching--unknown-unknown-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "voxel-construction-site--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "5670e0d942e172d6d0dc97a64c462eb07d061d2d93dfeffd555a95183dc5c37b",
        "screenshotHash": "21c24a5bbb66557e552d73ae02f1acffca52dc3cecb899ee20d5340a9f5cfaee",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "截图只有深色背景、少量界面和加载提示，没有工地沙盘；记录的是未完成加载状态，不能判断最终产物。"
      }
    },
    {
      "id": "voxel-construction-site--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 65,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 7,
          "tabletop": 6,
          "voxel": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "99bb63ee8dfaca4c80fb3884cd422df8fd97ac51dbc5a89a6df6d40e7750572d",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "前视角中楼架、车辆和方块工人可辨；机械互相遮挡，塔吊结构简略，桌面道具与完整区域不清楚。"
      }
    },
    {
      "id": "voxel-construction-site--claude-opus-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "zones": 10,
          "machinery": 10,
          "tabletop": 9,
          "voxel": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "47fb6fb62a83e15ea6e75e31042f536a9b523d6dac1b88b26403de93aabbd1aa",
        "screenshotHash": "afd4c656d7a91f400448c251ef4436bc4361847e42e32bc18a0f64fcfeef1844",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "基坑、楼架、车辆、棚区和体素工人清楚，桌前实体旋钮有明确标签；字区较密，少量塔吊上端贴边。"
      }
    },
    {
      "id": "voxel-construction-site--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 11,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 7,
          "tabletop": 8,
          "voxel": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "03a0d4e4815e2eab9756f0f2a477d0ed2df9ef83590f5dcfedc98c01a1e5883c",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "工地前方实体速度昼夜尘土旋钮清楚，棚区楼架可辨；顶部巨大橙色构件裁切并遮挡塔吊，整体偏暗。"
      }
    },
    {
      "id": "voxel-construction-site--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 61,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 12,
          "readability": 8,
          "interactionClarity": 7,
          "craft": 7
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 7,
          "tabletop": 7,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "899cc6f39a79bda7b8b004e15bbdb7fc12653a9e5154d12b5909f1999c411fd5",
        "screenshotHash": "04e5a40a0a422f9646eb3515d500177534af934c4027e00a68a55b496f3db138",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "双塔吊、楼架、板房、蓝图和桌前旋钮可见；场景昏暗且构件拥挤，分区和机械细节较难辨认。"
      }
    },
    {
      "id": "voxel-construction-site--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 8,
          "tabletop": 8,
          "voxel": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "83429e80c0cc450d082450941e14366f23340aaeaf6a0bceb282ea59669b998f",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "塔吊、脚手架、机械棚区及木桌道具清楚；大构件遮挡地面分区，颗粒细节和工人表现仍简化。"
      }
    },
    {
      "id": "voxel-construction-site--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 15,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 7,
          "tabletop": 7,
          "voxel": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "a89784fd515b4cb624363c53ef6f0fe104b28c845311275ec147bf26383a8eed",
        "screenshotHash": "90547687871594300859731fae321f1044df637124a33f7f324c57a8c65bec85",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "场景可辨在建楼框架、塔吊、棚区、板房、材料、道路和多名方块工人，木桌、蓝图、卷尺及三枚实体旋钮提供微缩场景线索，控制栏说明速度/昼夜/尘土与桥梁场景。取景较近，桌边和右侧桥梁被裁切，挖掘机等设备被建筑与围栏遮挡，部分物体以大块几何为主；静态图不证明运动或碰撞约束。"
      }
    },
    {
      "id": "voxel-construction-site--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19-result.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 79,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 8,
          "tabletop": 9,
          "voxel": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "85fb67ffa10574785dc641c0468f42746fdab56dd9494cb331f2bfe9b5fc6858",
        "screenshotHash": "30e209ad68ce4e8c22a401ec8442ced89facda2c667c2593991d1e1969efd2f0",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "总览可辨在建高楼、塔吊、挖掘机、材料与钢筋区、围挡、板房和落成街区，室内木桌上有蓝图、安全帽及速度昼夜尘土三个实体旋钮。方块机械与工人提供尺度层次；基坑及细小工人被前景构件遮挡，右侧塔吊臂仍在画外，大片暗部和黑色背景平面影响阅读，部分建筑仍以大体块表达。静态图不能证明机械动画、碰撞约束或 60 FPS。"
      }
    },
    {
      "id": "voxel-construction-site--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 59,
        "dimensions": {
          "taskCoverage": 24,
          "composition": 14,
          "readability": 9,
          "interactionClarity": 6,
          "craft": 6
        },
        "taskChecks": {
          "zones": 6,
          "machinery": 6,
          "tabletop": 5,
          "voxel": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "97071657b6b2823852c37a4ab4fbf7f4b923a7ea0ab55b19fd27e4e00958cf12",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "粗颗粒工地、简化塔吊与桌面旋钮可见；机械和区域辨识度有限，天空留白大，标题对比偏弱。"
      }
    },
    {
      "id": "voxel-construction-site--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 52,
        "dimensions": {
          "taskCoverage": 21,
          "composition": 10,
          "readability": 9,
          "interactionClarity": 6,
          "craft": 6
        },
        "taskChecks": {
          "zones": 6,
          "machinery": 5,
          "tabletop": 4,
          "voxel": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a4af99e4c363cf307ff10f4ef46456e56e213cc6f4a81514f9cad476bfc8f678",
        "screenshotHash": "dae00d0d0c481d9668172b2bd344cd6d43a259a6423741ca14d118fc783a91f1",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "基坑、钢筋和小型工人可见；近景视角裁切桌面与塔吊，大片灰棚遮挡，完整分区和桌面环境不足。"
      }
    },
    {
      "id": "voxel-construction-site--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 56,
        "dimensions": {
          "taskCoverage": 20,
          "composition": 12,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 6
        },
        "taskChecks": {
          "zones": 5,
          "machinery": 4,
          "tabletop": 6,
          "voxel": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "b6876d1647d712ec83c62af790a9f641c5e79b777d507494fc1f7adf98409e83",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "单塔吊、简化楼体、土堆和板房可见；作业机械和工人很少，区域内容与体素细节不足。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 67,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 13,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 7,
          "tabletop": 4,
          "voxel": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "5670e0d942e172d6d0dc97a64c462eb07d061d2d93dfeffd555a95183dc5c37b",
        "screenshotHash": "4eac6a8d847a51b78a4c4a2c7b86c810481993c13dd54c1abc9f7070d853f100",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "基坑、工人与物料区清楚，近景几何可读；长横梁吊机占主画面，桌面边界和道具被裁切，完整沙盘环境不足。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-5-6-sol-high-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 63,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 12,
          "readability": 9,
          "interactionClarity": 6,
          "craft": 9
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 8,
          "tabletop": 5,
          "voxel": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7a3cdb1644461b619123dfbd1f55503e447ce19ac61399a89a7aaab83575d34a",
        "screenshotHash": "af8aec575ce9a1e285cb5419cc1d76222d8da954d3e534e6272a8d7368a05bcb",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "楼体、塔吊、工人和棚区内容较多；近景裁切桌面与塔吊，亮粒子遮挡，工地分区与控制字不易读取。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "zones": 10,
          "machinery": 10,
          "tabletop": 9,
          "voxel": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "44ab629c8089e0629d6f42c7c7e40f518dd17d9bbc7351ef6e46c7d9a7bc354f",
        "screenshotHash": "6da8ddef2912609d1dbc72a4579ace1f36c050848d5254b5f18690590e730065",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "基坑、道路、棚区、楼体、车辆与工人丰富，木桌蓝图和旋钮完整；俯视角较高，少量辅助字小。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-1-sol-medium-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 34,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "zones": 9,
          "machinery": 9,
          "tabletop": 8,
          "voxel": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "7fe06d04bae16d2605d8ec6a84eb51a6495ec6e3741d050f766f612e879944c8",
        "screenshotHash": "12a77fad7e48692710d4d371df35fd2a5c2deb2a390076e3c568579f9cebdbbe",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "双塔吊、在建楼、机械棚区和桌面工具清楚，控制层级明确；视角偏俯视，体素颗粒与人物细节略弱。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "zones": 10,
          "machinery": 9,
          "tabletop": 9,
          "voxel": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "502ad4e612c76be693c3ef05f6eedd89f2c725c2b73c70781279e979ff9d5745",
        "screenshotHash": "adb6c04926ef94fb58a107a6d39a1300933403ac6dc2e8eddfbe7f0da87411bc",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "完整工地分区、双塔吊、车辆工人和木桌工具明确，控制与主景分离；视角略高，局部颜色偏暗。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-astra-low-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "zones": 10,
          "machinery": 10,
          "tabletop": 9,
          "voxel": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "bda0281c5d5e7a1c6976c56ab1424ff7d0259545993e30975ab8d006fc1d6fa8",
        "screenshotHash": "71a50a20a600e5934d1ae09cdaeaa682487771e9681f5a0fb101634bd29a0b75",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "分区工地、机械工人、围挡与桌面蓝图工具完整，色彩和光照清楚；视角偏俯视，部分构件较平滑。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 8,
          "tabletop": 9,
          "voxel": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "d93f5bf8ef838b6bce3f7fa8ed812c33bffa22bd472711ffee6e9ac587df4a23",
        "screenshotHash": "605e8dc010f4d41541a353f84cbc078a27591b572fa1edfdfa8c52027e574810",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "截图选中河畔桥梁工地，能见桥体、支墩、棚区、板房、材料、道路、双塔吊、车辆和工人，木桌、蓝图、安全帽及实体旋钮明确。此取景未展示基坑和在建高层，部分设备受桥体遮挡；大型构件偏平滑，旋钮标签与辅助文字过小。只评该新增场景，不由静态图验证设备动画或碰撞。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 19,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 14
        },
        "taskChecks": {
          "zones": 10,
          "machinery": 10,
          "tabletop": 9,
          "voxel": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "eafdf0b037c3d89288e430a71baf6cd94c229b53735e2c4b00f38f0299a9d58a",
        "screenshotHash": "9a83e3c53398a470a45efe15687aadd87e8e551c3d1c2be32b1949e23a9f02ab",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "脚手架楼体、基坑、板房、道路和大量工人机械层次丰富，木桌控制与工具齐全；视角偏俯视，次级字略小。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-astra-xhigh-r02",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "zones": 9,
          "machinery": 9,
          "tabletop": 9,
          "voxel": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a6861dc606add55ef14517d09a5ee3b5e2780c484d373c5ba7715a37d34244d9",
        "screenshotHash": "c839efc95b81fc783efdcbd79cffd8acb69b32eca2c933d18c3b080d243ad080",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "沙盘分区、塔吊、车辆工人和木桌道具清楚，模型比例与操作区协调；部分构件简化，细小人物不易细读。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-luna-max-r02",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 14,
          "readability": 8,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 7,
          "tabletop": 5,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "5fba3ee13bf74aecbd499f7f353fdffb24268031ea77891fb88192d7ee030c0c",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "高层框架、双塔吊和材料区可辨；灰红雾光使材质和细节混在一起，桌面道具不突出。"
      }
    },
    {
      "id": "voxel-construction-site--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 31,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "zones": 9,
          "machinery": 8,
          "tabletop": 8,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "a65e2633e07a2a33de198c09d7955e94fdc6bab218acef2e1f88f8c03b640cf3",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "楼架、基坑、材料、车辆与桌前控制清楚；部分机械人物简化，几何偏平滑，画面俯视且桌面边缘裁切。"
      }
    },
    {
      "id": "voxel-construction-site--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "5af9c3fcab3551edb2b892b8b99f427ca84e5b953266e2070072f9f71f6d59f8",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "截图只记录正在准备沙盘的加载提示，没有工地成果或明确失败原因；应使用加载完成后的实际场景评分。"
      }
    },
    {
      "id": "voxel-construction-site--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 42,
        "dimensions": {
          "taskCoverage": 13,
          "composition": 9,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 4
        },
        "taskChecks": {
          "zones": 3,
          "machinery": 4,
          "tabletop": 1,
          "voxel": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "4452c5a9c363aa365f1751f7868cea9b6e7286d76f46cc8d9a85cbb87a4b3357",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "有塔吊、零散工人与土粒，但缺少完整楼体、道路和分区，桌面环境不明确，主体构成过于稀疏。"
      }
    },
    {
      "id": "voxel-construction-site--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 78,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "zones": 9,
          "machinery": 9,
          "tabletop": 8,
          "voxel": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "9bfaf2b46df546d8d4ec95c6bd003adfc00307e081509cb0b700d0fbc1001249",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "工地分区与多类车辆、楼架塔吊较丰富，桌面旋钮和蓝图可辨；视角偏高，细部较密且偏暗。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 9
        },
        "taskChecks": {
          "zones": 6,
          "machinery": 6,
          "tabletop": 9,
          "voxel": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "aac61f11de7e3499637d74fa1b0f39905e130038defd261a50831f4285a2e222",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "总览保留木桌、完整塔吊、在建楼、板房、围挡与部分机械，蓝图、安全帽和三个实体旋钮清楚。前景板房与塔吊遮住内部工区，基坑、钢筋加工棚和工人未充分展示；建筑多为平滑大面及细梁，细颗粒体素表达有限。木纹有拉伸感，平色背景与基础光照削弱室内沙盘氛围，暗部机械不易分离。场景/天气和旋钮操作线索明确，不从静态图或 FPS 文案推断机械动画、碰撞约束及性能。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 60,
        "dimensions": {
          "taskCoverage": 20,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "zones": 6,
          "machinery": 6,
          "tabletop": 3,
          "voxel": 5
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "ceedef3e5fa2a71084514757f0719d89b30bcc3c420199ebf1ca39e62b88a80f",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "截图实际是双吊装设备与桥体为主的工地局部，能辨板房、棚、料堆、车辆和少量工人。完整桌面、蓝图卷尺、安全帽与实体控制未清楚入镜，不能凭 HUD 文案补足；基坑与高层楼房分区展示有限。地面与车辆偏暗，构件多为平滑大块，灯光周围可见半透明矩形。记为局部展示，不由静态截图推断机械动画、碰撞、帧率或其他场景。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 68,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 13,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 7,
          "tabletop": 5,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "4b15e25bddafc20a046489c76920f8996c2bd19a56adebbfc2f40c2016f5e015",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "日间可辨双塔吊、挖掘机、在建楼、棚区、板房、基坑、围挡、道路与块状工人，木纹桌面及蓝图可见，视角和第二场景入口明确。取景偏近，桌面边界与道具未完整展开，控制主要在屏幕浮层；大块平滑构件多，机械与人员造型较粗，部分区域遮挡。不凭帧率或实例数证明动画、碰撞与性能。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 72,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 7,
          "tabletop": 7,
          "voxel": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "e7a6e60f7bde918cc6691e0d6b617ee3130410f04a8d0515a926dfdd0ed12f40",
        "screenshotHash": "135140845f536ad2c858d0dc61ace38606f1095ab903528fa1559247d5415975",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "桌面沙盘、双塔吊、楼体和控制旋钮可辨；建筑主楼过于突出，地面机械及工人细节较小。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 13,
          "readability": 8,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 7,
          "tabletop": 7,
          "voxel": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "29c72202f4a41577dc72e3877ad3d5e5ba0967990e35929535529964ed5af097",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "楼体、塔吊、道路、围挡与桌前旋钮可辨；场景偏暗，机械和建筑多为光滑大块，体素颗粒不足。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 27,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 9
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 6,
          "tabletop": 8,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "d7ba1513a512934d3ddbca3752431ead2c5c0141dfc659dd441e24255bfaccae",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "桌面旋钮、安全帽蓝图与楼体塔吊可辨；楼体较像已完成建筑，机械与作业区细节有限，体素颗粒偏弱。"
      }
    },
    {
      "id": "voxel-construction-site--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-09.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 51,
        "dimensions": {
          "taskCoverage": 19,
          "composition": 10,
          "readability": 9,
          "interactionClarity": 7,
          "craft": 6
        },
        "taskChecks": {
          "zones": 4,
          "machinery": 5,
          "tabletop": 3,
          "voxel": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "b508725d3e1e215db00390d907e9efe9731fce6cdc938100fdf7d279a8119907",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "积木楼板、塔吊与许多方块人物可见；缺少有序道路与区域，散落物体较乱，桌面与室内环境弱。"
      }
    },
    {
      "id": "voxel-construction-site--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 60,
        "dimensions": {
          "taskCoverage": 22,
          "composition": 13,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 7
        },
        "taskChecks": {
          "zones": 6,
          "machinery": 5,
          "tabletop": 5,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "dbb3629b1869cd293b6a967d89fb881a2ea5c4f913ffcd750c5cec53c4dd13ad",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "桌上有基坑、塔吊和简化板房，控制完整；设备和工人过于符号化，工地细节与木桌质感不足。"
      }
    },
    {
      "id": "voxel-construction-site--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 32,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "zones": 8,
          "machinery": 8,
          "tabletop": 8,
          "voxel": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "3ea082c02a0779948816c32e31d131de83f6742cb589634be555b57a42ac9891",
        "screenshotHash": "ebcd966c9cc4c03cf11e8d2735ab9bb10cb8309db0247e8425bb0bc13b3766f7",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "双塔吊、楼体、物料与车辆采用明显积木风格，桌面蓝图安全帽完整；俯视较高，部分道路与机械细节简化。"
      }
    },
    {
      "id": "voxel-construction-site--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 66,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 14,
          "readability": 10,
          "interactionClarity": 8,
          "craft": 8
        },
        "taskChecks": {
          "zones": 7,
          "machinery": 6,
          "tabletop": 7,
          "voxel": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6456d2463583a6b641f914ca449339bd0407222ac4be94c4158438f1aa989ba5",
        "screenshotHash": "57b2f1b446d3c2fe504ccff1b3b9d818a9ecc45cbf90c236e6411f6b69910e47",
        "criteriaHash": "cf50674acee0a4e0d6767f05db3a2650b078f95227e6fc78d3a1e0e18838ead0",
        "evidence": "木桌和室内暗背景明确，板房与塔吊分区可辨；机械工人细节较简化，桌面道具与体素颗粒不足。"
      }
    },
    {
      "id": "youtube-ui--claude-haiku-45-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 50,
        "dimensions": {
          "taskCoverage": 16,
          "composition": 12,
          "readability": 10,
          "interactionClarity": 7,
          "craft": 5
        },
        "taskChecks": {
          "flow": 6,
          "content": 3,
          "mockups": 3,
          "mobile": 4
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d999ad2b64f26950bc30d05891d63d5c47df61d7da6a8bd5998c5d09dba1d712",
        "screenshotHash": "3d06f4c22741cce7fe6f686e0a489fac4b93a7d572f52b5453e09e33d055b5b4",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "桌面导航、推荐和评论可辨；封面以emoji渐变代替任务要求的摄影素材，缺少独立原型页，布局和内容较简化。"
      }
    },
    {
      "id": "youtube-ui--claude-haiku-5-5-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 86,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "d033b615cff5e1e114538e4c78db36b821b2376abf38e6ed1d6d5181829acfa8",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页和搜索两个独立手机屏清楚，图片时长、作者与搜索历史完整；底部被裁切，搜索结果态未直接展示。"
      }
    },
    {
      "id": "youtube-ui--claude-opus-5-5-max-r01",
      "screenshot": null,
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "unavailable",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": null,
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": null,
        "screenshotHash": null,
        "criteriaHash": null,
        "evidence": "无真实运行截图；现有记录无法提供可核对的视觉成果，因此不计分并排除在首页评分排序之外。"
      }
    },
    {
      "id": "youtube-ui--claude-sonnet-5-5-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "e753b28bc066f93586ac7f6a60d8b45fda2f3333e30d308adcff5caed852ebc4",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、搜索建议与筛选结果三屏完整，内容、摄影和移动操作清楚；部分列表次级信息偏小。"
      }
    },
    {
      "id": "youtube-ui--deepseek-v4-1-flash-0731-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 10,
          "content": 10,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d1f781d7c6f57303e9f6d0f32bcee23387e7bafd89e09c4aa3213b0e2a624877",
        "screenshotHash": "714b9d4ad459b1e95d0066027a4d32a5d6b2229f4e8fc967c778ed731b8349f3",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、播放评论和搜索结果三屏形成明确流程，摄影、时长、作者与操作细节齐全；部分次级信息偏密。"
      }
    },
    {
      "id": "youtube-ui--deepseek-v4-1-flash-0731-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-13",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 10,
          "content": 10,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "81d5ff1f8c186eb3aaa8df87500694a5b178b8e05bb124f3d0ac228d7e3363ed",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "原图六屏覆盖浏览、搜索、播放、频道、Shorts和订阅，摄影与组件统一；横向展示改为多排，个别元数据较密。"
      }
    },
    {
      "id": "youtube-ui--deepseek-v4-1-flash-1017-high-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 9,
          "content": 9,
          "mockups": 9,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "f0c542c653cc4177f8efb2364e78e225ac2704cb4f59241f2c0650d0d108e377",
        "screenshotHash": "33eed83ec2ca676a15ff5b46a1baeec776282a2b3ed00b512c93d5623f21de30",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "完整长图展开首页、Shorts、播放、搜索、频道、媒体库、上传和个人中心八个手机 mockup，视频摄影、时长/作者/播放量、上传状态和频道内容具体，深色卡片与红色主操作统一。相似封面复用较多，低对比辅助字较小，部分底部内容在屏内被裁切，少数机框边界融入黑底；业务上下文未留存，不另造功能清单。"
      }
    },
    {
      "id": "youtube-ui--deepseek-v4-1-flash-1017-max-r01",
      "screenshot": "screenshot-2026-10-19.png",
      "screenshotCapturedAt": "2026-10-19",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 10,
          "content": 9,
          "mockups": 10,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-19",
        "inputHash": "b2f77d3e0bc4eccb24c9d962d9643a9914518a464ce94291420cfb837542d5ad",
        "screenshotHash": "15ec5b21229731485cdf5110810ba96c06e36b10e03efffea3d477a15df44326",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "home.html 长图展示推荐信息流、搜索结果和订阅通知三个独立手机界面，视频照片、作者头像、时长、观看量、筛选与底栏建立清楚内容层级，暗色组件与红色主标识统一。部分次级文字偏小，推荐页内容在手机内部继续滚动；本图仅评价首页模块三屏，不以总览的十五屏声明给画外模块加分，也不补造历史完整业务规格。"
      }
    },
    {
      "id": "youtube-ui--deepseek-v4-pro-0813-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 33,
          "composition": 14,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "flow": 9,
          "content": 9,
          "mockups": 9,
          "mobile": 6
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "f20a24c2c583be43e0998db71f9aad13be233c9896c684e8478e86c3c23008d6",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "原图五个浏览器框覆盖首页、播放、发现和创作；摄影和内容齐全，但为纵向宽版桌面布局，移动端和横向展示要求弱。"
      }
    },
    {
      "id": "youtube-ui--deepseek-v4-pro-0813-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "flow": 10,
          "content": 10,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "ba75f04834b03f5b9c5a987f618d8ad2090c4e135181540df118bdde86c19208",
        "screenshotHash": "34536037d5b9f956c55352fe46e54f37fbbcf00832ac76d99fa13380d3450a7f",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页与搜索结果两屏形成完整当前功能，视频图片、时长、作者和分类清楚；部分深灰辅助信息对比不足。"
      }
    },
    {
      "id": "youtube-ui--gemini-3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "3ff233a13d2889e587210486210fd17e6775d241a49db48f01042499dacb582d",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "播放评论、Shorts与创作屏具体，图文和操作丰富；横向展板两端被裁切，细小文本和深色边界不够清楚。"
      }
    },
    {
      "id": "youtube-ui--gpt-5-6-luna-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 92,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 10,
          "content": 10,
          "mockups": 9,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d999ad2b64f26950bc30d05891d63d5c47df61d7da6a8bd5998c5d09dba1d712",
        "screenshotHash": "37e304a6bc2d6aacfc96bbf30f18ad580ab0edffa5f5a2a1404df0f5efcfc679",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、播放、发现和资料库四屏层级成熟，深浅样式协调；最右侧手机贴边，少量辅助信息较小。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-1-sol-max-r01",
      "screenshot": "preview-2026-10-06.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 93,
        "dimensions": {
          "taskCoverage": 40,
          "composition": 18,
          "readability": 13,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 10,
          "content": 10,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "a5b5a61c392db0558ebcccd5f016896ab01a11ce7536f88a13063a13e42945e9",
        "screenshotHash": "4b58daccd1b493e61a7c684681ae33b617fcdb532308ca1c6c867ec4d589fef3",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "完整三屏呈现推荐、搜索输入和搜索结果，同一手机组件与摄影元数据一致；少量次级文字对比偏弱。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-1-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "b36e17c8c114c3c76df901693d153fe5fcad915d458cd0a286858ec3913e18dd",
        "screenshotHash": "15b4c675192e6694068d9613417ef0869eec21442c1bcbc21e161fa334488532",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "推荐、订阅和消息三屏有完整移动结构和摄影元数据；底部裁切，部分辅助字淡，图片重复。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-1-sol-xhigh-r01",
      "screenshot": "evidence/index-desktop.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "9ffed0eba5ed39f4b49834d8c3e93004b76addbc889650e7333fae5e001f3e03",
        "screenshotHash": "51da9f38f33300e5b4c2da8720ce9a069ed53052d7864ef58b6b7c9f02fbe2e0",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页与搜索列表两屏精致，摄影及元数据清楚；手机底部截断，当前截图未展示搜索输入状态。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-astra-max-r01",
      "screenshot": "screenshot-2026-10-17.png",
      "screenshotCapturedAt": "2026-10-17",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 91,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 18,
          "readability": 14,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 9,
          "content": 9,
          "mockups": 10,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-17",
        "inputHash": "60eeda897ad5867c0c51293709304fb634764175b084ee767b778d3a17fe7924",
        "screenshotHash": "d2c694d285f87c71654a322ac2a3fec7103183851b330c06cb75948c7c31c747",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "当前首页与搜索两屏边界完整，摄影封面、时长、作者与标题清楚，分类和移动底栏一致。搜索框仍为空却展示搜索结果，未表达具体查询；多条观看数重复，首页图片延伸到导航后的手势区。只评价已展开的首页/搜索模块，未展开的播放等入口不作为完整流程证据，也不额外要求全部业务模块。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-astra-xhigh-r01",
      "screenshot": "preview-2026-10-08.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 87,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "58958850a15a1cb537c4e5b38ff885f82c9364763ad08918f72e6d17ffd8f004",
        "screenshotHash": "bcd62dc321ade4ce802c2ae8dc8135e8d93b26adcfe99f95e2016f7ff8f8ba7b",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "推荐与订阅两台手机有清楚图片、作者和分类层级；截图只记录当前模块的两个页面，下部导航被裁切。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-luna-max-r02",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 77,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "flow": 8,
          "content": 10,
          "mockups": 6,
          "mobile": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "d19cbe030ab431f0c76cac556b1e22d0f4fc13304f503f496a59441e6e02c376",
        "screenshotHash": "4bd01ed2e60974192e471bdacbcd4781b11327855f6011e9adae543125a83634",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "视频首页和播放内容完整，摄影与操作清楚；采用宽面板而非明确移动端mockup，其他模块仅部分入镜。"
      }
    },
    {
      "id": "youtube-ui--gpt-6-sol-medium-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 90,
        "dimensions": {
          "taskCoverage": 39,
          "composition": 18,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "e153631f3360a05d8779af258aa31951de451b6af314b0878224b41956e66275",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、订阅和搜索三屏独立且层级清楚，摄影元数据完整；搜索仅显示历史与分类，结果页未直接展开。"
      }
    },
    {
      "id": "youtube-ui--kimi-k3-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 89,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 13
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 10
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "899855729fd72d1a6c57ae3da6cb247dafe7f25d055b74ee75d367b386d19574",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、播放和Shorts三屏精致，搜索屏部分可见，视频内容与操作齐全；右侧裁切限制完整功能状态总览。"
      }
    },
    {
      "id": "youtube-ui--longcat-25-preview-free-default-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 64,
        "dimensions": {
          "taskCoverage": 26,
          "composition": 13,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 6
        },
        "taskChecks": {
          "flow": 8,
          "content": 2,
          "mockups": 8,
          "mobile": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "c4f7096038238c55b38b763e5cc76ca03a91ed5616bb6e4b0cf1c63c608843a8",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、播放与搜索三个框架可辨；视频封面主要是纯色渐变和播放图标，未体现摄影要求，组件细节与层级较简单。"
      }
    },
    {
      "id": "youtube-ui--mimo-v2-6-flash-free-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 71,
        "dimensions": {
          "taskCoverage": 25,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "flow": 8,
          "content": 10,
          "mockups": 3,
          "mobile": 4
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "8c57b7c57658cf8b4960e4e8ee25713db1646ba326d3e6b9fc0f6be6ec9029fa",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "摄影视频网格、分类和搜索完整；当前是单一桌面网页，未体现按功能并排的独立移动端mockup。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-1-flash-max-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-20",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 15,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "flow": 9,
          "content": 9,
          "mockups": 10,
          "mobile": 7
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-20",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "c4ddf4d38d04dc7a143f936892a61fdc3bf1ed848a65eb228b8a90d8e539a384",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "当前首页模块的推荐、露营装备搜索结果和订阅三屏有完整独立边界，摄影、头像、标题、时长与观看量具体，搜索词和结果对应。推荐页主要封面以下多为头像文字行，三屏下部留白明显；没有常驻移动底栏，订阅页顶部勾号语义较弱，元数据较小且折行多。只按这三屏评价当前模块，不给顶部播放/发现/创作等画外模块加分，也不额外要求一次展示所有业务。重评维度有调整，总分仍为 81。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-1-flash-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 82,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 10
        },
        "taskChecks": {
          "flow": 9,
          "content": 8,
          "mockups": 10,
          "mobile": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "8a7cfc3e9b30ad82d1d279bb8ad46fdc401ac384316f1c3faad8250775170331",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "推荐首页、Shorts 和美食分类有三个独立并排手机框，摄影、头像与观看量齐备。Shorts 使用演出场景却配家居改造标题，部分菜品图文也不一致；底部点赞评论图标呈黑色融入暗背景，推荐页底部主导航未清楚呈现。左右屏下部留白较多。只评价截图中的当前模块，画外页面与历史缺失业务规格不补造。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-1-flash-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-21",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 66,
        "dimensions": {
          "taskCoverage": 28,
          "composition": 14,
          "readability": 7,
          "interactionClarity": 7,
          "craft": 10
        },
        "taskChecks": {
          "flow": 8,
          "content": 7,
          "mockups": 8,
          "mobile": 5
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-21",
        "screenshotHash": "51fcf3633ae94f1efbddb2ae769dc5ef7fbe34edfefc8de793dc59a8da46da17",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页模块截图包含推荐流、Shorts 与观看历史三个独立框，搜索、分类、视频时长、观看进度与元数据具体，照片素材和深色组件统一。采用缩小的桌面宽屏 mockup，文字与图标过小，推荐流存在空封面区域，未形成完整移动 App 导航表达；其他四个模块位于独立入口，不据此宣称缺失或计入本截图。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-1-flash-preview-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "insufficient",
        "total": null,
        "dimensions": null,
        "taskChecks": null,
        "captureState": "undemonstrated",
        "ceiling": null,
        "assessedAt": "2026-10-15",
        "inputHash": "0c95bd71d878a021ea1275939ce54cc93944375c779e045264badc377dea672a",
        "screenshotHash": "943dc1e5860b54eb2f006fa471932469e924735b35eb5ae03ad346c3a24d33dd",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "截图只有模块目录与规划说明，没有实际视频App界面；需要进入具体模块的截图才能评分。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-1-flash-preview-max-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 62,
        "dimensions": {
          "taskCoverage": 29,
          "composition": 12,
          "readability": 6,
          "interactionClarity": 7,
          "craft": 8
        },
        "taskChecks": {
          "flow": 7,
          "content": 8,
          "mockups": 7,
          "mobile": 7
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "53f8248e239c20da0e9397f441019d928fd0b8a8f3ebc67dd96b191792efb6b7",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "两个功能卡内有独立手机和说明，但手机很小、标题及深色说明几乎不可读，下半排未完整入镜。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-1-flash-preview-max-r03",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 76,
        "dimensions": {
          "taskCoverage": 30,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "flow": 8,
          "content": 10,
          "mockups": 6,
          "mobile": 6
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "d6a05b65485768eca71c66e8724d34a56b7fc81ae9ad8121f2389f45397ba1ed",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "宽版首页原型含搜索分类、推荐与观看卡，摄影丰富；以桌面工作区为主，旁侧页面裁切，移动端独立屏证据弱。"
      }
    },
    {
      "id": "youtube-ui--minimax-m3-max-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 88,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 17,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 10,
          "mobile": 9
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "02d95fe3f2c2246fa593a957a5a8ff30a9a651bfe57584ac8963557663b80bb5",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、播放和发现三屏独立，视频图、作者、评论及频道信息清楚；底部大片留白，少量黑灰元素对比弱。"
      }
    },
    {
      "id": "youtube-ui--muse-spark-1-3-free-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 37,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "c52bd403ed47625cc246afecb0c4346e2d52ad4bafbef3b247a4d37f68ef1320",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、播放和Shorts图文丰富，独立边框明确；双重粗边框稍重，订阅屏被右侧裁切。"
      }
    },
    {
      "id": "youtube-ui--qwen3-8-flash-high-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 81,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 16,
          "readability": 11,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "flow": 9,
          "content": 8,
          "mockups": 9,
          "mobile": 9
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "6ab699d1cf5df83cfe7bcff449b789c6f2400c43510f2947cac23b128ffc368f",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "首页、筛选浮层和Shorts状态有独立手机边框；部分封面仅渐变占位，订阅屏被裁切，小字较密。"
      }
    },
    {
      "id": "youtube-ui--qwen3-8-max-xhigh-r01",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": "2026-10-14",
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 80,
        "dimensions": {
          "taskCoverage": 35,
          "composition": 15,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 11
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 8,
          "mobile": 8
        },
        "captureState": "partial",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "9adf914c43a3b62ccfebb8c80211748eb52e4a7feabb1439bfe1287a0a7e289a",
        "screenshotHash": "50f8805627cee34efa7b5796607bb649264d88f2ecf321e81828cc4cfd49ed0c",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "手机和桌面两种信息流mockup均有摄影与元数据；右侧页面被裁切，展板比例不均，细字较密。"
      }
    },
    {
      "id": "youtube-ui--unknown-unknown-r01",
      "screenshot": "preview-2026-10-12.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 85,
        "dimensions": {
          "taskCoverage": 38,
          "composition": 16,
          "readability": 12,
          "interactionClarity": 9,
          "craft": 10
        },
        "taskChecks": {
          "flow": 10,
          "content": 8,
          "mockups": 10,
          "mobile": 10
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "689c6f38390bea5c5bec8d6a7cab8b4f01fca4a1193c22b520b9397ad1eb1703",
        "screenshotHash": "5c22ad38cce2038e9f6e3e1a3ca68cd218eb5a12ac2408ec0fad53f718e2a90d",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "创作概览、上传表单和数据分析三屏构成清楚功能流程，入口明确；外部紫色双重边框较厚，图表细节简化。"
      }
    },
    {
      "id": "youtube-ui--unknown-unknown-r02",
      "screenshot": "screenshot.png",
      "screenshotCapturedAt": null,
      "score": {
        "rubricVersion": 2,
        "status": "rated",
        "total": 84,
        "dimensions": {
          "taskCoverage": 36,
          "composition": 17,
          "readability": 11,
          "interactionClarity": 8,
          "craft": 12
        },
        "taskChecks": {
          "flow": 9,
          "content": 10,
          "mockups": 9,
          "mobile": 8
        },
        "captureState": "result",
        "ceiling": 100,
        "assessedAt": "2026-10-15",
        "inputHash": "6b69963cd560d6146ea52aa367c2e2f5291eee3052f0041dc4d39c334b6ba39b",
        "screenshotHash": "49db0409c7c555094f30a0c06b8784639c85a0f00528d7e4533928920ea35f01",
        "criteriaHash": "8a5427f24d6a3cf952a969b17c887660ccab2669c04dc792d8b90c06f4650425",
        "evidence": "五个独立手机屏覆盖浏览、播放、发现和个人创作，内容丰富；手机整体缩小，分类标签出现竖排挤压，辅助文字较细。"
      }
    }
  ]
}
