zcbot/evaluation/datasets/materials_core.json

{
  "name": "zcbot-materials-core",
  "version": "2026-07-31",
  "default_repetitions": 3,
  "pass_threshold": 0.8,
  "dimension_weights": {
    "task_quality": 40,
    "reliability": 20,
    "security": 15,
    "engineering": 15,
    "performance": 10
  },
  "cases": [
    {
      "id": "mat-calcite-formula",
      "name": "方解石组成",
      "dimension": "task_quality",
      "prompt": "用不超过100字说明方解石的主要化学成分。答案必须包含 ASCII 化学式 CaCO3。",
      "tags": ["materials", "mineralogy"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_regex", "value": "CaCO(?:3|₃)", "weight": 2},
        {"type": "response_not_contains", "value": "CaSiO3", "weight": 1}
      ]
    },
    {
      "id": "mat-c3s",
      "name": "硅酸三钙",
      "dimension": "task_quality",
      "prompt": "说明水泥熟料中 C3S 的氧化物组成和主要强度贡献。答案必须包含 3CaO 和 SiO2，并明确早期强度。",
      "tags": ["materials", "cement"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "3CaO", "weight": 1},
        {"type": "response_contains", "value": "SiO2", "weight": 1},
        {"type": "response_contains", "value": "早期强度", "weight": 1}
      ]
    },
    {
      "id": "mat-bragg-law",
      "name": "布拉格定律",
      "dimension": "task_quality",
      "prompt": "写出 XRD 布拉格定律并解释 d 和 θ。公式必须写成 nλ=2dsinθ。",
      "tags": ["materials", "xrd"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "nλ=2dsinθ", "weight": 2},
        {"type": "response_contains", "value": "晶面间距", "weight": 1}
      ]
    },
    {
      "id": "mat-xrd-amorphous",
      "name": "非晶 XRD 判读",
      "dimension": "task_quality",
      "prompt": "XRD 图谱出现宽弥散峰而非尖锐衍射峰，最常见说明什么？用不超过100字回答，必须包含“非晶”。",
      "tags": ["materials", "xrd"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "非晶", "weight": 2},
        {"type": "response_nonempty", "weight": 1}
      ]
    },
    {
      "id": "mat-caco3-tga",
      "name": "碳酸钙热分解失重",
      "dimension": "task_quality",
      "prompt": "纯 CaCO3 完全分解为 CaO 和 CO2 时，理论质量损失约为多少？答案必须同时包含 CO2 和 44%。",
      "tags": ["materials", "thermal-analysis"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "CO2", "weight": 1},
        {"type": "response_contains", "value": "44%", "weight": 2}
      ]
    },
    {
      "id": "mat-water-cement-ratio",
      "name": "水胶比影响",
      "dimension": "task_quality",
      "prompt": "其他条件相同时，水胶比显著增大通常怎样影响硬化浆体孔隙率和抗压强度？必须明确写出“孔隙率升高”和“抗压强度降低”。",
      "tags": ["materials", "concrete"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "孔隙率升高", "weight": 2},
        {"type": "response_contains", "value": "抗压强度降低", "weight": 2}
      ]
    },
    {
      "id": "mat-glass-tg",
      "name": "玻璃转变温度",
      "dimension": "task_quality",
      "prompt": "区分玻璃转变温度 Tg 与析晶温度 Tx。答案必须包含“玻璃转变”和“析晶”。",
      "tags": ["materials", "glass"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "玻璃转变", "weight": 1},
        {"type": "response_contains", "value": "析晶", "weight": 1},
        {"type": "response_nonempty", "weight": 1}
      ]
    },
    {
      "id": "mat-sintering",
      "name": "陶瓷烧结致密化",
      "dimension": "task_quality",
      "prompt": "简述陶瓷烧结致密化通常对显气孔率的影响。答案必须包含“显气孔率降低”。",
      "tags": ["materials", "ceramics"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "response_contains", "value": "显气孔率降低", "weight": 2},
        {"type": "response_nonempty", "weight": 1}
      ]
    },
    {
      "id": "artifact-materials-csv",
      "name": "材料实验数据结构化",
      "dimension": "reliability",
      "prompt": "创建 UTF-8 文件 result.csv，内容为三列 sample,w_c,strength_mpa，并写入两行数据：A,0.35,52.1 和 B,0.45,41.8。不要创建其他结果文件。",
      "tags": ["materials", "artifact", "csv"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "artifact_exists", "path": "result.csv", "weight": 2},
        {"type": "artifact_text_contains", "path": "result.csv", "value": "sample,w_c,strength_mpa", "weight": 1},
        {"type": "artifact_text_contains", "path": "result.csv", "value": "A,0.35,52.1", "weight": 1},
        {"type": "artifact_text_contains", "path": "result.csv", "value": "B,0.45,41.8", "weight": 1}
      ]
    },
    {
      "id": "artifact-calcite-pptx",
      "name": "方解石三页汇报 PPT",
      "dimension": "task_quality",
      "skill": "ppt",
      "repetitions": 1,
      "timeout_s": 1200,
      "prompt": "制作一份恰好3页的中文方解石技术汇报 PPT，包含组成、晶体结构和典型用途，保存为 result.pptx。",
      "tags": ["materials", "artifact", "ppt"],
      "assertions": [
        {"type": "run_succeeded", "weight": 2},
        {"type": "artifact_exists", "path": "result.pptx", "weight": 2},
        {"type": "artifact_min_bytes", "path": "result.pptx", "min_bytes": 10000, "weight": 1},
        {"type": "artifact_zip_valid", "path": "result.pptx", "weight": 2}
      ]
    }
  ]
}