{ "method_version": "grandet-website-review-v1", "evaluates": "website correctness and usability within its declared local historical-preview scope, not provider/model quality", "score_max": 100, "check_scoring": { "PASS": 5, "FAIL": 0, "NOT_CHECKED": null }, "checks": [ { "id": "I01", "label": "模型身份边界", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "原始名称数、规范模型数、配置/规则数分别命名；未知不被宣传为独立模型。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Model identity boundaries", "passCriteriaEn": "Recorded-name counts, canonical-model counts and configuration/rule counts are labelled separately; unresolved items are not advertised as independent models." }, { "id": "I02", "label": "归属依据", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "每条映射含明确 status、依据/规则版本；仅字符串相似只能候选归属，不能变成供应商实供认证。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Attribution evidence", "passCriteriaEn": "Every mapping has an explicit status and an evidence or rule version. String similarity alone permits only a candidate attribution and cannot certify actual supplier delivery." }, { "id": "I03", "label": "非模型和版本", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "测试/操作/通配符规则单列；快照、模态、上下文/预算/渠道参数不静默剥离；冲突保留。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Non-model entries and versions", "passCriteriaEn": "Tests, operations and wildcard rules are separate; snapshots, modalities, context, budgets and channel parameters are not silently stripped, and conflicts are retained." }, { "id": "I04", "label": "双向检索", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "规范模型能到全部相关声明/报价；精确原名能找回归属与全部原价；未归属有入口。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Two-way lookup", "passCriteriaEn": "A canonical model leads to all associated declarations and quotes; an exact recorded name retrieves its attribution and all original prices; unresolved items remain accessible." }, { "id": "S01", "label": "零售主体与域名", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "来源站点、品牌、已核实运营主体分别显示；域名数不冒称独立供应商数。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Retail operators and domains", "passCriteriaEn": "Source hosts, brands and verified legal operators are distinguished; domain counts are not presented as independent-supplier counts." }, { "id": "S02", "label": "上游和渠道", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "上游声明与已核实上游分开；来源前缀不冒称真供应链；套餐/分组保留。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Upstream and channels", "passCriteriaEn": "Declared upstreams and verified upstreams remain distinct; a source prefix does not certify a supply chain, and plans/groups are retained." }, { "id": "S03", "label": "供应商覆盖", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "所有采集站点可搜索/定位；详情不会因 20 模型旧白名单漏数据；数量范围清晰。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Supplier coverage", "passCriteriaEn": "Every captured host is searchable or locatable; detail views do not omit data because of the old 20-model allowlist, and count scopes are explicit." }, { "id": "P01", "label": "原价/计费保真", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "全部现金标签、积分、按次、公式及未知原值可定位；未知不补零，原始 lexeme/单位保留。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Original prices and billing fidelity", "passCriteriaEn": "Cash labels, credits, per-request values, formulas and unknown original fields are all locatable. Unknowns are not replaced with zero; original numeric lexemes and units are retained." }, { "id": "P02", "label": "可比范围", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "模型身份、协议、配置、上下文、期次、现金兑换、费用完整性有据才称可比；原始排序有显式限定。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Comparison scope", "passCriteriaEn": "Comparability requires evidence for model identity, protocol, configuration, context, capture period, cash conversion and fee completeness; original-value sorting states its limits." }, { "id": "P03", "label": "计算正确", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "同范围输入/输出比例及单位正确；有理数避免误排；按次/特殊计费不被 Token 公式处理；缓存和费用条件可见。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Calculation correctness", "passCriteriaEn": "Input/output shares and units are correct within the same scope; rational arithmetic prevents misordering; per-request and special billing are not processed as Token prices; cache and fee conditions are visible." }, { "id": "P04", "label": "时间/资格", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "采集日和期次可见；旧记录不当当前报价；未核现金、账户、费用和独立主体阈值不生成正式现金名次。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Time and qualification", "passCriteriaEn": "Observation dates and capture periods are visible; historical records are not presented as current quotes. No formal cash rank is generated without verified cash, account, fee and independent-operator requirements." }, { "id": "Q01", "label": "四种结论分开", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "官方模型能力、端点实测、文档披露、价格资格分别呈现与引用；不借名声推断端点。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Separate four kinds of conclusions", "passCriteriaEn": "Original-creator model capability, endpoint measurements, documentation disclosure and price qualification are presented and cited separately; reputation is not used to infer endpoint performance." }, { "id": "Q02", "label": "缺失与来源", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "无样本/过期/不足门槛显示未知，分数为 null；每个已发布分数均可回溯样本/方法/窗口。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Missing data and provenance", "passCriteriaEn": "Missing samples, expired evidence and insufficient coverage remain unknown with null scores; every published score is traceable to samples, method and observation window." }, { "id": "Q03", "label": "可执行方法", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "公开文档分检查项/阈值，公开质量维度/测量定义/公式/样本和公布门槛，明确当前未测及方法状态。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Executable methodology", "passCriteriaEn": "Documentation checks and thresholds, and quality dimensions, measurement definitions, formulas, sample gates and publication gates are public; the current unmeasured state and method status are explicit." }, { "id": "D01", "label": "源到导出全覆盖", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "独立读取 PART2/PART3 的源行/配置指针，与导出 stable ID 集合一致；缺失/意外重复均 0。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Complete source-to-export coverage", "passCriteriaEn": "An independent read of PART2/PART3 source rows and configuration pointers matches exported stable-ID sets; missing entries and unintended duplicates both equal zero." }, { "id": "D02", "label": "导出到UI全覆盖", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "raw/rate/config/catalog/orphan 的预期展开 ID 集与实际 boardRecords 相等；每个筛选可清除、不默认漏未归属。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Complete export-to-display coverage", "passCriteriaEn": "Expected expanded IDs for raw records, rates, configurations, legacy catalog entries and orphan records equal those produced by boardRecords; every filter can be cleared, and unresolved entries are not omitted by default." }, { "id": "D03", "label": "证据完整", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "URL/原文摘要或安全原始文件/JSON 指针/哈希/观察时间可回溯；未知和空来源明确；不泄露凭据。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Evidence completeness", "passCriteriaEn": "URLs, source excerpts or safe original files, JSON pointers, hashes and observation times are traceable; unknown and empty sources are explicit; credentials are not exposed." }, { "id": "U01", "label": "核心交互", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "桌面/手机实际验证模型与站点检索、切换、分页、刷新直达、筛选重置、详情/下载；加载失败可重试且不冒充完整。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Core interactions", "passCriteriaEn": "Desktop and mobile checks verify model/host search, switching, pagination, direct refresh, filter reset, details and downloads; failed loads are retryable and do not appear complete." }, { "id": "U02", "label": "客户端服务一致", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "持久服务正常；SSR/客户端名称、数据与结果一致；核心浏览器无未捕获错误；构建及回归通过。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Client and server consistency", "passCriteriaEn": "The persistent preview service works; server-rendered and client names, data and results agree; core browser flows have no uncaught errors; build and regression checks pass." }, { "id": "G01", "label": "可读可引用", "weight": 5, "status": "NOT_CHECKED", "evidence": [], "passCriteria": "SSR 有可读身份/价/状态，站点方法与机器数据概念一致；中英文用词一致；本地 noindex 与未上线状态诚实。", "failCriteria": "任一必要条件经核查不成立，或存在与本检查相关的未关闭 P0/P1 问题。", "notCheckedCriteria": "未执行本项全部必要核验，或结果缺少可定位证据。", "requiredEvidence": [ "revision or source-data hash", "executable check or reproducible browser steps", "observed result", "reviewed at", "reviewer" ], "labelEn": "Readable and citable output", "passCriteriaEn": "Server-rendered pages expose readable identities, prices and status; page methodology and machine data use consistent concepts; Chinese and English wording agrees; local noindex and undeployed status are truthful." } ], "pass_gates": { "all_checks_executed": true, "minimum_score": 95, "open_P0": 0, "open_P1": 0, "independent_review_required": true, "claim_scope": "No known unresolved P0/P1 within executed checks; not universal bug absence" }, "definition_source": "/public-data/website-review-rubric.json", "live_inference_performed": false, "provider_quality_score": null, "provider_measurement_method_proposal": "grandet-endpoint-measurement-v1-proposal", "selfContainedCriteria": true, "scoreFormula": "If any check is NOT_CHECKED, total = null; otherwise total = sum(PASS ? weight : 0).", "severityGates": { "P0": [ "原始数据丢失或跨记录覆盖", "秘密泄露", "伪造实测、模型身份或现金资格", "把未知价格作为免费", "主要页面无法使用" ], "P1": [ "系统性混淆模型与渠道/规则", "跨不可比单位宣称便宜", "供应商详情或索引遗漏", "未评分当0分", "搜索/刷新导致主要记录不可达", "把原厂基准转移到未经测试中转站" ], "P2": "不影响事实正确性、范围完整性与主要功能的表达或便利性问题；须记录影响。" }, "reviewCycle": [ "Initial evaluation against these fixed criteria", "Fix all discovered P0/P1 problems and justified P2 problems", "Rerun affected checks and required regression suite", "Independent review of resulting behavior", "Stop only after all checks executed, score >=95, P0/P1=0 and every discovered blocking issue reverified closed" ] }