agent-comparability 0.5.2__py3-none-any.whl

agent_comparability/__init__.py

@@ -0,0 +1,3 @@
+"""Agent Comparability — cmp/0.3.1 参考实现。"""
+from .core import CDR, adjudicate, POLICY_VERSION
+__version__ = "0.5.2"

agent_comparability/core.py

@@ -0,0 +1,113 @@
+"""比较判定核心库 cmp/core（cmp/0.3.1 规范参考实现，第十九轮升级）。
+
+相对 0.2 的规范符合性修复（依据 SPEC 0.3.1；B 集冻结预期先于本修改存在）：
+  ①同任务性检查入 score 判定优先级 2（B3 暴露 0.2 缺失）
+  ②评分尺度一致性检查（含 0.3.1 隐式默认规则）（B4/B5 暴露 0.2 缺失）
+  ③claim 路由补 registration/descriptive 关键词（B2-B5 暴露误判）
+  ④policy_version 升 cmp/0.3.1（消费方按 SPEC §5 重判旧 CDR）
+判定优先级（SPEC §3.3）：INCONCLUSIVE(缺trace) > INADMISSIBLE(任务/模型/混淆/尺度) > PARTIAL(零语义) > ADMISSIBLE。
+"""
+
+from dataclasses import dataclass, field, asdict
+
+POLICY_VERSION = "cmp/0.3.1"
+TAMPER_LIMITATION = "摘要一致仅证明未同步修改，不构成抗恶意篡改（单写信任域）"
+DEFAULT_SCALE = {"range": "0..1", "unit": "fraction", "verifier": "source"}
+KNOWN_FIELDS = {"task_id", "harness", "model", "reward", "reward_status",
+                "trajectory_available", "score_scale", "repetition_count"}
+
+
+@dataclass
+class CDR:
+    case_id: str
+    requested_claim: str
+    comparison_scope: str
+    admissibility: str = "PENDING"
+    satisfied_conditions: list = field(default_factory=list)
+    violated_conditions: list = field(default_factory=list)
+    unknown_conditions: list = field(default_factory=list)
+    supported_claims: list = field(default_factory=list)
+    unsupported_claims: list = field(default_factory=list)
+    evidence_refs: list = field(default_factory=list)
+    policy_version: str = POLICY_VERSION
+    limitations: list = field(default_factory=lambda: [TAMPER_LIMITATION])
+
+    def to_dict(self):
+        return asdict(self)
+
+
+def _effective_scale(r):
+    """SPEC 0.3.1 隐式默认：值∈[0,1] 且未声明 → 默认尺度；否则必须显式。"""
+    if "score_scale" in r:
+        return tuple(sorted(r["score_scale"].items()))
+    if isinstance(r.get("reward"), (int, float)) and 0.0 <= r["reward"] <= 1.0:
+        return tuple(sorted(DEFAULT_SCALE.items()))
+    return None  # 越界且未声明 → 不一致
+
+
+def adjudicate(case: dict, requested_claim: str) -> CDR:
+    recs = case["records"]
+    models = {r["model"] for r in recs}
+    harnesses = {r["harness"] for r in recs}
+    tasks = {r["task_id"] for r in recs}
+    statuses = [r["reward_status"] for r in recs]
+    any_missing = any(r.get("trajectory_available") is False for r in recs)
+    multi = len(recs) > 1
+    ignored = sorted({k for r in recs for k in r if k not in KNOWN_FIELDS})
+
+    cdr = CDR(case_id=case["id"], requested_claim=requested_claim,
+              comparison_scope=f"{len(recs)} records; models={sorted(models)}; harnesses={sorted(harnesses)}")
+
+    (cdr.satisfied_conditions if len(tasks) == 1 else cdr.violated_conditions).append("same_task_id")
+    (cdr.satisfied_conditions if len(models) == 1 else cdr.violated_conditions).append("same_model")
+    confounded = len(models) > 1 and len(harnesses) > 1
+    (cdr.violated_conditions if confounded else cdr.satisfied_conditions).append("single_variable_isolation")
+    if any_missing:
+        cdr.violated_conditions.append("trace_available")
+    if "unresolved_zero" in statuses and "verified" in statuses:
+        cdr.violated_conditions.append("zero_semantics_uniform(verified_zero != unresolved_zero)")
+    scales = [_effective_scale(r) for r in recs]
+    if (multi and (None in scales or len(set(scales)) > 1)) or None in scales:
+        # 值越界且未声明尺度（单记录同样不构成可比较尺度）——SPEC 0.3.1 隐式默认规则
+        cdr.violated_conditions.append("score_scale_consistent")
+    else:
+        base = scales[0] if scales else tuple(sorted(DEFAULT_SCALE.items()))
+        cdr.satisfied_conditions.append("continuous_score_preserved(" + repr(dict(base)) + ")")
+    if ignored:
+        cdr.unknown_conditions.append(f"ignored_fields:{ignored}")
+    if any_missing:
+        cdr.unknown_conditions.append("source_reward_retained_but_unverifiable_by_us")
+
+    claim = requested_claim.replace("_", " ")
+    single_var = (not confounded and not any_missing)
+
+    if any(k in claim for k in ("causal", "导致", "归因")):
+        cdr.admissibility = "INADMISSIBLE"
+        cdr.unsupported_claims.append("causal_attribution(单次运行无重复)")
+        if single_var:
+            cdr.supported_claims.append("descriptive_side_by_side(降级表述)")
+    elif any(k in claim for k in ("score", "分数", "成功率")) and not any(
+            k in claim for k in ("record", "登记", "registration", "descriptive")):
+        if any_missing:
+            cdr.admissibility = "INCONCLUSIVE"
+            cdr.supported_claims.append("score_transcription(source_verifier_attested)")
+            cdr.unsupported_claims.append("success_rate(含证据缺失记录)")
+        elif len(tasks) > 1 or len(models) > 1 or confounded or "score_scale_consistent" in cdr.violated_conditions:
+            cdr.admissibility = "INADMISSIBLE"
+            cdr.unsupported_claims.append("score_comparison(任务/模型/尺度条件冲突)")
+        elif any(v.startswith("zero_semantics_uniform") for v in cdr.violated_conditions):
+            cdr.admissibility = "PARTIAL"
+            cdr.supported_claims.append("per_status_stratified_rate(verified_zero/unresolved_zero 分列)")
+            cdr.unsupported_claims.append("pooled_fail_rate(0 分语义混同)")
+        else:
+            cdr.admissibility = "ADMISSIBLE"
+            cdr.supported_claims.append("continuous_score_side_by_side(同尺度)")
+    elif any(k in claim for k in ("record", "登记", "registration", "descriptive", "describe")):
+        cdr.admissibility = "ADMISSIBLE"
+        cdr.supported_claims.append("descriptive_registration(全部条件+连续分数)")
+    else:
+        cdr.admissibility = "INCONCLUSIVE"
+        cdr.unknown_conditions.append("unrecognized_claim_type")
+
+    cdr.evidence_refs = [f"rec:{r['task_id']}/{r['model']}/{r['harness']}" for r in recs]
+    return cdr

agent_comparability/data/SPEC.md

@@ -0,0 +1,115 @@
+# Agent Evaluation Comparability Specification — cmp/0.3.1 (Release Candidate)
+
+规范状态：候选规范（非行业标准、无第三方认证）。本文是判定语义的单一事实来源；参考实现（`scripts/cmp/core.py`）与一切第三方实现均以本文为准，冲突时以本文裁决。可脱离任何源码阅读。
+
+---
+
+## 0. 范围与目的
+
+给定一组**评测运行记录**（Record）与一个**请求结论**（Requested Claim），本规范定义：该组记录在当前证据条件下**允许得出什么结论、不允许得出什么结论**。它不评分、不运行 Agent、不替代任何评测框架——它只裁决**可比性**。
+
+**Record**（最小字段）：`task_id`、`model`、`harness`、`reward`（数值）、`reward_status`（`verified` / `unresolved_zero` / 其他）、可选 `trajectory_available`（bool）、可选 `score_scale`（`{range, unit, verifier}`）、可选 `repetition_count`（int ≥1）。
+
+---
+
+## 1. 证据信任层级（独立于比较判定）
+
+每条 Record 的评分只能落在以下一层，层级**互斥且必须显式**，不得混用：
+
+| 层 | 名称 | 含义 | 禁止 |
+|---|---|---|---|
+| L-claim | agent-claimed | Agent 自我声明 | 作为评分依据 |
+| L-src | source-verifier-attested | 来源基准验证器给出 | 冒充本方独立验证 |
+| L-ours | independently-verified | 本方对终态/答案亲自复验 | — |
+| L-none | no-sufficient-evidence | trace 缺失/截断/引用不一致 | 计入任何成功率 |
+
+**摘要（哈希）一致 = binding_verified，仅证明"未经同步修改"，不构成抗恶意篡改**（单写信任域）。该限制必须出现在每个 CDR 的 `limitations` 中。
+
+---
+
+## 2. Requested Claim 类型
+
+| 类型 | 语义 |
+|---|---|
+| `causal` | 断言某变量（模型/Harness）**导致**了分数差异 |
+| `score_comparison` | 请求对连续分数做（并排或汇总）比较 |
+| `descriptive_registration` | 仅登记条件与分数，不作比较结论 |
+| 其他 | **未支持类型** |
+
+未支持类型 → `INCONCLUSIVE`，`unknown_conditions` 记录 `unrecognized_claim_type`。**实现不得猜测**相近类型。
+
+---
+
+## 3. Admissibility 分类与判定优先级
+
+### 3.1 分类
+
+| 分类 | 含义 |
+|---|---|
+| `ADMISSIBLE` | 所请求结论类型在当前条件下可得出 |
+| `INADMISSIBLE` | 条件冲突，该结论类型**不可**得出（较弱结论可能仍可） |
+| `PARTIAL` | 结论可得出但必须按拆分形式呈现（不得合并） |
+| `INCONCLUSIVE` | 证据不足以判定（保留数据，不删来源评分） |
+
+### 3.2 前置条件检查（按此顺序求值并记入 CDR）
+
+1. `same_task_id` —— 全部 Record 同任务
+2. `same_model` —— 全部同模型
+3. `single_variable_isolation` —— **不得同时变化两个及以上比较变量**（模型与 Harness 同时不同即违反）
+4. `trace_available` —— 无 `trajectory_available=false`
+5. `zero_semantics_uniform` —— `verified` 的 0 分与 `unresolved_zero` 的 0 分**语义不同**，混组即违反
+6. `score_scale_consistent` —— 全部 Record 声明同一 `{range, unit, verifier}`。**隐式默认规则（0.3.1 勘误补充）**：当组内全部 `reward ∈ [0,1]` 且未声明 `score_scale` 时，视为声明默认尺度 `{range:"0..1", unit:"fraction", verifier:"source"}`；任一值越界（如 0..100 百分制）或显式声明互不一致即违反。缺省与显式混用亦违反。
+7. `causal_evidence_available` —— `repetition_count ≥ 1` 的重复实验存在于每个比较单元
+
+### 3.3 判定表（规范核心）
+
+**`causal`**：无条件 `INADMISSIBLE`，除非 3.2-7 满足（重复实验存在）；满足时仍须在 `supported_claims` 中**降级表述**为描述性结论。禁止单次运行支持因果。
+
+**`score_comparison`**（按优先级，先命中先裁决）：
+1. 违反 `trace_available` → `INCONCLUSIVE`（来源评分转录保留于 `unknown_conditions`，禁止删除）
+2. 违反 `single_variable_isolation` **或** `same_task_id` 或 `same_model` → `INADMISSIBLE`
+3. 违反 `score_scale_consistent` → `INADMISSIBLE`
+4. 违反 `zero_semantics_uniform` → `PARTIAL`（支持按 verified/unresolved 分列的率；禁止合并 fail 率）
+5. 其余 → `ADMISSIBLE`（同尺度连续分数并排）
+
+**`descriptive_registration`**：无条件 `ADMISSIBLE`（登记一切条件与连续分数原值）。
+
+优先级说明：证据缺失（INCONCLUSIVE）先于条件冲突（INADMISSIBLE）裁决，因为前者连"冲突"都无从判定；冲突先于语义拆分（PARTIAL），因为混变量组连拆分比较也不支持。
+
+---
+
+## 4. 变量变化对比较的影响
+
+| 变化 | score_comparison | descriptive_registration |
+|---|---|---|
+| 仅 Harness 不同（同任务同模型） | ADMISSIBLE（并排） | ADMISSIBLE |
+| 仅模型不同（同任务同 Harness） | ADMISSIBLE（并排） | ADMISSIBLE |
+| 模型与 Harness 同时不同 | INADMISSIBLE | ADMISSIBLE |
+| 任务不同 | INADMISSIBLE | ADMISSIBLE |
+| 评分尺度/验证器不同 | INADMISSIBLE | ADMISSIBLE（附尺度差异说明） |
+| reward_status 语义混同 | PARTIAL（分列） | ADMISSIBLE |
+
+---
+
+## 5. 未知字段、未支持 Claim 与版本规则
+
+- **未知字段**：Record 中规范未定义的字段**必须忽略**（不得报错、不得猜测），并在 `unknown_conditions` 记 `ignored_fields:[...]`。
+- **未支持 Claim**：见 §2 —— INCONCLUSIVE + `unrecognized_claim_type`，禁止近似匹配。
+- **Policy 版本**：CDR 必须携带 `policy_version`。消费方遇到 `policy_version` 不认识时**必须丢弃该 CDR 并重新判定**，不得部分信任。本规范为 `cmp/0.3.1`（0.3 的澄清版：仅补隐式默认尺度规则，判定表未变）。
+- **规范不兼容变更**：升 minor（0.3→0.4）可新增判定分支；改判定表必须升 major 并迁移案例。
+
+---
+
+## 6. CDR（Comparison Decision Record）最小字段
+
+`case_id`、`requested_claim`、`comparison_scope`、`admissibility`、`satisfied_conditions[]`、`violated_conditions[]`、`unknown_conditions[]`、`supported_claims[]`、`unsupported_claims[]`、`evidence_refs[]`、`policy_version`、`limitations[]`（必须含 §1 防篡改声明）。机器可验证 Schema：`release/cdr.schema.json`。
+
+---
+
+## 7. Conformance 分层（三个独立指标，禁止合并）
+
+1. **集成一致性**（integration）：同一参考实现经不同框架（Inspect/Pydantic）调用，输出逐字段一致。
+2. **规范一致性**（spec conformance）：独立实现（仅依本文、未读参考源码）对冻结案例的判定与冻结预期一致。
+3. **策略正确性**（policy correctness）：参考实现对冻结案例的判定与冻结预期一致。
+
+三者的失败含义不同：1=适配缺陷；2=规范有歧义或实现误读；3=参考实现缺陷。任何"9/9"只属于其所属层。

agent_comparability/data/boundary-cases.json

@@ -0,0 +1,38 @@
+{
+  "frozen_at": "2026-10-25T21:00:00Z",
+  "note": "边界案例集 B1-B8：全部未参与 core.py 任何一轮调试；含合法与非法配置；预期判定先冻结后运行。B3/B4/B5 是对 cmp/0.2 的规范性 gap 检验（同任务性/尺度一致性/摘要不匹配在 0.2 中缺失，0.3 规范已补）。",
+  "cases": [
+    {"id": "B1", "desc": "未支持 claim 类型（ranking）",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 1.0, "reward_status": "verified"}],
+     "claims": {"ranking": "INCONCLUSIVE"}},
+    {"id": "B2", "desc": "未知字段忽略不报错",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 1.0, "reward_status": "verified", "mystery_field": "x", "another": 42}],
+     "claims": {"descriptive_registration": "ADMISSIBLE", "score_comparison": "ADMISSIBLE"}},
+    {"id": "B3", "desc": "不同任务混组做分数比较（规范 gap 检验）",
+     "records": [{"task_id": "t-a", "harness": "h1", "model": "m1", "reward": 1.0, "reward_status": "verified"},
+                  {"task_id": "t-b", "harness": "h1", "model": "m1", "reward": 0.0, "reward_status": "verified"}],
+     "claims": {"score_comparison": "INADMISSIBLE", "descriptive_registration": "ADMISSIBLE"}},
+    {"id": "B4", "desc": "评分尺度不一致（规范 gap 检验）",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 0.9, "reward_status": "verified",
+                   "score_scale": {"range": "0..1", "unit": "fraction", "verifier": "v1"}},
+                  {"task_id": "t", "harness": "h1", "model": "m1", "reward": 90, "reward_status": "verified",
+                   "score_scale": {"range": "0..100", "unit": "percent", "verifier": "v2"}}],
+     "claims": {"score_comparison": "INADMISSIBLE", "descriptive_registration": "ADMISSIBLE"}},
+    {"id": "B5", "desc": "尺度元数据缺失（全值在 [0,1]）",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 0.9, "reward_status": "verified"},
+                  {"task_id": "t", "harness": "h2", "model": "m1", "reward": 0.8, "reward_status": "verified"}],
+     "claims": {"score_comparison": "ADMISSIBLE", "descriptive_registration": "ADMISSIBLE"},
+     "erratum": "初冻结预期为 INADMISSIBLE（保守），与更早冻结的 A 集（C1/C3/C5 同为无声明全 [0,1] 值且预期 ADMISSIBLE/PARTIAL）矛盾——独立实现暴露该矛盾后，依'旧冻结优先'原则修正为 ADMISSIBLE 并在 SPEC 0.3.1 增补隐式默认尺度规则。此为公开勘误，非为通过测试改预期（A 集未动）。"},
+    {"id": "B6", "desc": "重复实验存在时的因果请求（仍降级）",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 1.0, "reward_status": "verified", "repetition_count": 3},
+                  {"task_id": "t", "harness": "h2", "model": "m1", "reward": 0.0, "reward_status": "verified", "repetition_count": 3}],
+     "claims": {"causal": "INADMISSIBLE", "score_comparison": "ADMISSIBLE"}},
+    {"id": "B7", "desc": "单条记录 score_comparison（退化但合法）",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 0.66, "reward_status": "verified", "score_scale": {"range": "0..1", "unit": "fraction", "verifier": "v1"}}],
+     "claims": {"score_comparison": "ADMISSIBLE"}},
+    {"id": "B8", "desc": "混组+缺 trace 同时存在（优先级检验：INCONCLUSIVE 先于 INADMISSIBLE）",
+     "records": [{"task_id": "t", "harness": "h1", "model": "m1", "reward": 1.0, "reward_status": "verified"},
+                  {"task_id": "t", "harness": "h2", "model": "m2", "reward": 0.0, "reward_status": "verified", "trajectory_available": false}],
+     "claims": {"score_comparison": "INCONCLUSIVE"}}
+  ]
+}

agent_comparability/data/cdr.schema.json

@@ -0,0 +1,89 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "cmp/cdr-0.3.schema.json",
+  "title": "Comparison Decision Record (cmp/0.3)",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "case_id",
+    "requested_claim",
+    "comparison_scope",
+    "admissibility",
+    "satisfied_conditions",
+    "violated_conditions",
+    "unknown_conditions",
+    "supported_claims",
+    "unsupported_claims",
+    "evidence_refs",
+    "policy_version",
+    "limitations"
+  ],
+  "properties": {
+    "case_id": {
+      "type": "string"
+    },
+    "requested_claim": {
+      "type": "string"
+    },
+    "comparison_scope": {
+      "type": "string"
+    },
+    "admissibility": {
+      "enum": [
+        "ADMISSIBLE",
+        "INADMISSIBLE",
+        "PARTIAL",
+        "INCONCLUSIVE"
+      ]
+    },
+    "satisfied_conditions": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "violated_conditions": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "unknown_conditions": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "supported_claims": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "unsupported_claims": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "evidence_refs": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "policy_version": {
+      "type": "string",
+      "pattern": "^cmp/0\\.3(\\.1)?$"
+    },
+    "limitations": {
+      "type": "array",
+      "minItems": 1,
+      "description": "必须包含防篡改声明",
+      "contains": {
+        "type": "string",
+        "pattern": "抗恶意篡改|tamper"
+      }
+    }
+  }
+}

agent_comparability/data/frozen-cases-a.json

@@ -0,0 +1,51 @@
+{
+  "policy_version": "cmp/0.2.0",
+  "frozen_note": "案例与参考判定先于三路运行冻结",
+  "cases": [
+    {
+      "id": "C1",
+      "category": "same-task-same-model-diff-harness",
+      "expected_admissibility_by_claim": {
+        "score_compare": "ADMISSIBLE",
+        "causal": "INADMISSIBLE"
+      }
+    },
+    {
+      "id": "C2",
+      "category": "same-task-diff-model-diff-harness",
+      "expected_admissibility_by_claim": {
+        "score_compare": "INADMISSIBLE",
+        "record": "ADMISSIBLE"
+      }
+    },
+    {
+      "id": "C3",
+      "category": "verified-vs-unresolved-zero",
+      "expected_admissibility_by_claim": {
+        "score_compare": "PARTIAL"
+      }
+    },
+    {
+      "id": "C4",
+      "category": "missing-trace",
+      "expected_admissibility_by_claim": {
+        "score_compare": "INCONCLUSIVE",
+        "record": "ADMISSIBLE"
+      }
+    },
+    {
+      "id": "C5",
+      "category": "score-scale-variation",
+      "expected_admissibility_by_claim": {
+        "score_compare": "ADMISSIBLE"
+      }
+    },
+    {
+      "id": "C6",
+      "category": "provenance-binding",
+      "expected_admissibility_by_claim": {
+        "record": "ADMISSIBLE"
+      }
+    }
+  ]
+}

agent_comparability-0.5.2.dist-info/METADATA

@@ -0,0 +1,351 @@
+Metadata-Version: 2.4
+Name: agent-comparability
+Version: 0.5.2
+Summary: Agent evaluation comparability semantics: spec + conformance suite + thin reference implementation
+License: Apache-2.0
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Provides-Extra: suite
+Requires-Dist: pyyaml; extra == "suite"
+Requires-Dist: jsonschema; extra == "suite"
+Provides-Extra: inspect
+Requires-Dist: inspect-ai; extra == "inspect"
+Provides-Extra: pydantic
+Requires-Dist: pydantic-evals; extra == "pydantic"
+Dynamic: license-file
+
+<div align="center">
+
+# Agent Comparability
+
+**Experimental Specification & Conformance Suite** for AI agent evaluation comparability
+
+[![CI](https://github.com/Rethymus/agent-comparability/actions/workflows/ci.yml/badge.svg)](https://github.com/Rethymus/agent-comparability/actions/workflows/ci.yml)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-3776AB?logo=python&logoColor=white)](pyproject.toml)
+
+**English** | [简体中文](README.zh-CN.md)
+
+*When can you compare AI agent evaluation results — and what claims do they support?*
+
+</div>
+
+---
+
+> [!IMPORTANT]
+> This project adjudicates **comparability of evaluation records** — it does **not** run
+> agents, score benchmarks, or certify any agent's reliability. Passing the conformance
+> suite means *specification* conformance, nothing more.
+
+**The 30-second path**: [Install](#6-installation) → [Quickstart](#7-quickstart) →
+[Real input/output](#8-inputoutput-example-actual-output).
+
+<details open>
+<summary><b>Table of Contents</b></summary>
+
+1. [Project Overview](#1-project-overview)
+2. [Problem & Motivation](#2-problem--motivation)
+3. [What Agent Comparability Does](#3-what-agent-comparability-does)
+4. [What It Does Not Do](#4-what-it-does-not-do)
+5. [Main Features](#5-main-features)
+6. [Installation](#6-installation)
+7. [Quickstart](#7-quickstart)
+8. [Input/Output Example (actual output)](#8-inputoutput-example-actual-output)
+9. [Architecture](#9-architecture)
+10. [Conformance Suite](#10-conformance-suite)
+11. [Inspect AI / Pydantic Evals Integrations](#11-inspect-ai--pydantic-evals-integrations)
+12. [Specification & Versioning](#12-specification--versioning)
+13. [Limitations](#13-limitations)
+14. [Contributing](#14-contributing)
+15. [Security](#15-security)
+16. [License & Acknowledgements](#16-license--acknowledgements)
+
+[FAQ](#faq) · [Project status](#project-status)
+
+</details>
+
+---
+
+## 1. Project Overview
+
+Agent Comparability is a framework-independent **specification** ([spec/SPEC.md](spec/SPEC.md)),
+a frozen **conformance suite**, and a thin **reference implementation** that adjudicates
+*comparability* of agent evaluation records — never the scores themselves.
+
+**Who is this for**: developers comparing agent/prompt/harness evaluation results,
+benchmark authors documenting what conclusions their data supports, and teams building
+reliability pipelines on top of existing eval frameworks.
+
+### How it relates to existing tools
+
+| Tool | What it does | Relation to Agent Comparability |
+|---|---|---|
+| [Inspect AI](https://inspect.aisi.org.uk) | Runs evals, agents, sandboxes | Complementary — Inspect *executes*; this decides what comparisons its results support. Adapter provided. |
+| [Pydantic Evals](https://pydantic.dev) | Datasets, cases, reporting | Complementary reporting layer over the same core. Adapter provided. |
+| Benchmark harnesses (lm-eval, SWE-bench, …) | Measure models | They *produce* records; this adjudicates what comparisons of those records mean |
+
+## 2. Problem & Motivation
+
+Three failure modes silently corrupt agent-evaluation conclusions:
+
+| Failure mode | What actually goes wrong |
+|---|---|
+| **Semantics mixing** | A *verified failure* and an *unresolved zero* both read `0.0` — pooled "fail rates" become meaningless |
+| **Confounded variables** | Model and harness change at the same time — a two-variable diff gets reported as causation |
+| **Evidence gaps** | Missing traces quietly inflate success rates; rankings reverse across harnesses |
+
+These boundaries should be **machine-checkable**, not vibes. That is what this project ships.
+
+## 3. What Agent Comparability Does
+
+- Adjudicates a **Requested Claim** (e.g. `score_comparison`, `causal`,
+  `descriptive_registration`) against a set of evaluation records
+- Returns a **Comparison Decision Record (CDR)**: admissibility
+  (`ADMISSIBLE / INADMISSIBLE / PARTIAL / INCONCLUSIVE`), satisfied/violated/unknown
+  conditions, **supported claims AND forbidden claims**, evidence refs, policy version
+- Enforces evidence-trust tiers (agent-claimed vs source-verifier vs independently
+  verified), score-scale consistency (range/unit/verifier), zero-semantics splits,
+  and unknown-field/unknown-claim rules
+- Ships a frozen conformance suite run against three separated metrics
+
+**Admissibility quick reference** (full priority rules in [SPEC §3.3](spec/SPEC.md)):
+
+| Verdict | Meaning | Typical trigger |
+|---|---|---|
+| `ADMISSIBLE` | Requested conclusion is supported | Same task / model / score scale, all records verified |
+| `INADMISSIBLE` | Conclusion not supported | Confounded variables, task mismatch, or score-scale mismatch |
+| `PARTIAL` | Only split presentation allowed | `verified` failures mixed with `unresolved_zero` |
+| `INCONCLUSIVE` | Evidence insufficient to judge | Missing traces / evidence anchors |
+
+## 4. What It Does Not Do
+
+> [!WARNING]
+> - Does **not** run agents, benchmarks, or models; no network, no credentials, no Docker
+> - Does **not** score anything or certify any agent's reliability
+> - Never merges its three conformance metrics into one number (see [§10](#10-conformance-suite))
+
+## 5. Main Features
+
+- `adjudicate(records, requested_claim) -> CDR` — pure Python, zero dependencies
+- Priority-ordered decision table (evidence-missing > confounded > semantics > admissible)
+- Machine-verifiable CDR JSON Schema ([spec/cdr.schema.json](spec/cdr.schema.json))
+- Frozen A/B conformance case sets; B5 public erratum precedent protected
+- Optional adapters for Inspect AI and Pydantic Evals reusing the same core
+
+## 6. Installation
+
+From PyPI (first published release: `0.5.2`):
+
+```bash
+pip install agent-comparability                            # minimal core, zero deps
+pip install "agent-comparability[suite]"                   # + suite basics (pyyaml, jsonschema)
+pip install "agent-comparability[suite,inspect,pydantic]"  # FULL conformance run
+```
+
+From a clone (development):
+
+```bash
+git clone https://github.com/Rethymus/agent-comparability.git && cd agent-comparability
+pip install -e .                        # minimal core, zero deps
+pip install -e .[suite]                 # + suite basics (pyyaml, jsonschema)
+pip install -e .[suite,inspect,pydantic]  # FULL conformance run — required by run_suite.py
+```
+
+Requires Python ≥ 3.10. No Docker, no model keys.
+
+## 7. Quickstart
+
+```python
+from agent_comparability import adjudicate
+
+cdr = adjudicate({"id": "demo", "records": [
+    {"task_id": "t1", "harness": "h1", "model": "m1",
+     "reward": 1.0, "reward_status": "verified"},
+    {"task_id": "t1", "harness": "h2", "model": "m1",
+     "reward": 0.0, "reward_status": "unresolved_zero"}]},
+    "score_comparison")
+```
+
+## 8. Input/Output Example (actual output)
+
+> Note: the reference implementation's condition/claim messages are currently in Chinese; the admissibility verdict itself is locale-neutral.
+
+The quickstart call returns:
+
+```
+cdr.admissibility      -> PARTIAL
+cdr.supported_claims   -> ['per_status_stratified_rate(verified_zero/unresolved_zero 分列)']
+```
+
+A confounded group instead:
+
+```python
+cdr = adjudicate({"id": "x", "records": [
+    {"task_id": "a", "harness": "h1", "model": "m1", "reward": 1.0, "reward_status": "verified"},
+    {"task_id": "b", "harness": "h2", "model": "m2", "reward": 0.0, "reward_status": "verified"}]},
+    "score_comparison")
+```
+
+```
+cdr.admissibility       -> INADMISSIBLE
+cdr.violated_conditions -> ['same_task_id', 'same_model', 'single_variable_isolation']
+```
+
+`cdr.to_dict()` emits the full CDR (schema-validated). The quickstart call's complete
+CDR — actual output:
+
+```json
+{
+  "case_id": "demo",
+  "requested_claim": "score_comparison",
+  "comparison_scope": "2 records; models=['m1']; harnesses=['h1', 'h2']",
+  "admissibility": "PARTIAL",
+  "satisfied_conditions": [
+    "same_task_id",
+    "same_model",
+    "single_variable_isolation",
+    "continuous_score_preserved({'range': '0..1', 'unit': 'fraction', 'verifier': 'source'})"
+  ],
+  "violated_conditions": [
+    "zero_semantics_uniform(verified_zero != unresolved_zero)"
+  ],
+  "unknown_conditions": [],
+  "supported_claims": [
+    "per_status_stratified_rate(verified_zero/unresolved_zero 分列)"
+  ],
+  "unsupported_claims": [
+    "pooled_fail_rate(0 分语义混同)"
+  ],
+  "evidence_refs": [
+    "rec:t1/m1/h1",
+    "rec:t1/m1/h2"
+  ],
+  "policy_version": "cmp/0.3.1",
+  "limitations": [
+    "摘要一致仅证明未同步修改，不构成抗恶意篡改（单写信任域）"
+  ]
+}
+```
+
+## 9. Architecture
+
+```
+spec/SPEC.md                     ← single source of truth (readable standalone)
+spec/cdr.schema.json             ← machine-verifiable CDR
+src/agent_comparability/core.py  ← thin reference implementation
+src/agent_comparability/data/    ← SPEC + schema + frozen cases (packaged)
+conformance/                     ← run_suite.py (3 metrics) + independent_impl.py + cases
+adapters/                        ← optional inspect-ai / pydantic-evals wrappers
+tests/                           ← smoke + property tests
+```
+
+Adjudication flow (priority order, per [SPEC §3.3](spec/SPEC.md)):
+
+```mermaid
+flowchart LR
+    A[Records + Requested Claim] --> B{trace available?}
+    B -- missing --> C[INCONCLUSIVE]
+    B -- ok --> D{task / model /<br/>score scale consistent?}
+    D -- conflict --> E[INADMISSIBLE]
+    D -- ok --> F{zero semantics uniform?}
+    F -- verified + unresolved mixed --> G[PARTIAL]
+    F -- ok --> H[ADMISSIBLE]
+    C & E & G & H --> V[CDR<br/>supported + forbidden claims]
+```
+
+## 10. Conformance Suite
+
+`python conformance/run_suite.py` reports three **separated** metrics that must
+never be merged:
+
+1. **Policy correctness** — reference implementation vs frozen expectations
+2. **Spec conformance** — an independent implementation written from SPEC alone
+3. **Integration consistency** — the same core via Inspect/Pydantic adapters
+
+A failure in each means a different defect class (implementation bug / spec
+ambiguity or misread / adapter bug).
+
+The full suite run requires the adapter extras (`.[suite,inspect,pydantic]`) — a missing adapter is treated as FAIL, not skipped.
+
+## 11. Inspect AI / Pydantic Evals Integrations
+
+```bash
+pip install -e .[inspect] && python adapters/inspect_adapter.py
+pip install -e .[pydantic] && python adapters/pydantic_adapter.py
+```
+
+Both wrap the *same* core (no semantic duplication). Inspect scorer uses
+`metrics=[]` — admissibility is deliberately **not** aggregated into accuracy.
+The Pydantic evaluator checks the **task's real output** (`ctx.output`) against
+frozen expectations — it never re-adjudicates inside the evaluator — and the
+adapter's exit code derives from the full 22-pair `report` (cases + failures).
+
+## 12. Specification & Versioning
+
+Three distinct lines: software tag (e.g. `v0.5.0`), specification `cmp/0.3.1`
+(inside SPEC), and `agent_comparability.__version__`. Judgment-table changes
+require a spec major bump (SPEC §5). See [CHANGELOG](CHANGELOG.md) for the full tag lineage
+(v0.3.1–v0.3.6 are deprecated candidates kept immutably for the record).
+
+## 13. Limitations
+
+- Experimental specification; self-tested conformance, **no external certification**
+- Single-writer trust domain: digest equality proves non-divergence, not
+  tamper-resistance (SPEC §1)
+- No repetition/cost modeling inside adjudication (handled by callers)
+- Chinese/English docs kept equivalent; translation drift tracked in CI link checks
+
+## FAQ
+
+**Does passing the conformance suite certify my agent is reliable?**
+No. It certifies that an *implementation* matches the specification. It says nothing about any agent.
+
+**Can I use it with my existing eval framework?**
+Yes. The core is framework-independent (`adjudicate()` is a pure function over record
+dicts). Adapters for Inspect AI and Pydantic Evals are included; any framework whose
+output you can map to the [record schema](spec/SPEC.md#0-范围与目的) works.
+
+**Why not just compare scores?**
+Because `0.0` can mean a *verified failure* or an *unresolved zero*; because model and
+harness changing together turns a diff into an unfounded causal claim; and because
+missing traces inflate success rates silently. §2's failure modes are all real-world
+artifacts, not hypotheticals.
+
+**Does it run agents or benchmarks?**
+No — no network, no credentials, no Docker. It only ever sees the records you pass in.
+
+**Which versions should I depend on?**
+Package `v0.5.0+` (version lines unified and CI-enforced since then); specification
+`cmp/0.3.1` evolves independently — see [§12](#12-specification--versioning).
+
+## Project status
+
+| Component | Status |
+|---|---|
+| Specification `cmp/0.3.1` | Stable — frozen conformance set anchors it |
+| Claim types | `score_comparison`, `causal`, `descriptive_registration` (+ unknown → `INCONCLUSIVE`) |
+| Conformance cases | 22 frozen pairs (A + B sets), three separated metrics, all green in CI |
+| Adapters | Inspect AI ✓ · Pydantic Evals ✓ |
+| CI gates | Terminal scan · bilingual docs · conformance ×3 · tests · release version · build + twine · package content |
+| Repo governance | `main` protected (PR + required check), release tags `v*` immutable |
+| Distribution | PyPI (`agent-comparability`, since `0.5.2`, Trusted Publishing) + GitHub source/tags |
+
+## 14. Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). Key rule: **never edit frozen expectations
+to make tests pass**; errata follow the public B5 precedent. PRs must pass all
+three conformance metrics separately.
+
+## 15. Security
+
+See [SECURITY.md](SECURITY.md). Private vulnerability reporting preferred.
+
+## 16. License & Acknowledgements
+
+Apache-2.0 (see [LICENSE](LICENSE), [NOTICE](NOTICE)). Optional integrations
+inspect-ai / pydantic-evals are MIT and **not bundled**. Conformance case data is
+original to this project; no CC BY-NC data is distributed. Research lineage:
+this repo was distilled from a private research repository; internal process
+records live under `docs/internal/`.

agent_comparability-0.5.2.dist-info/RECORD

@@ -0,0 +1,13 @@
+agent_comparability/__init__.py,sha256=_lzqbqMVJzU3Ghht2aJ_7IXi7Edp9pi-BAh4j4-jOEk,128
+agent_comparability/core.py,sha256=FSeZbP9eMffF4No0vxg5lhG-qJsH6Fvq3ly8m0j0qVA,6130
+agent_comparability/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+agent_comparability/data/SPEC.md,sha256=RUO1sYy0JNgZ3DCHy9FRGmFQOxZbRZUKKU5QaplmOGE,7044
+agent_comparability/data/boundary-cases.json,sha256=yDmBTi75jyzaCgwmLvPF08gW43LgoVMAF8D2Ud4OJKk,3808
+agent_comparability/data/cdr.schema.json,sha256=xdcLCz-8plIqu85xwGWojJ4R-IzjSByrcXgu1E2jjQQ,1870
+agent_comparability/data/frozen-cases-a.json,sha256=ryQIfK52TIQp7U4iskmccVZpyoRIq5ryvIvnujw-Vwc,1257
+agent_comparability-0.5.2.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+agent_comparability-0.5.2.dist-info/licenses/NOTICE,sha256=Hilay-w5cb1_H5fXQ8AkTPf11vo58Al6cijsokeqwYc,462
+agent_comparability-0.5.2.dist-info/METADATA,sha256=7hYC9T4loqIZZT2HloxaXSAAxwfuvAmn7h8XVfoR99M,14650
+agent_comparability-0.5.2.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+agent_comparability-0.5.2.dist-info/top_level.txt,sha256=snGm9R4SnpPifGHC6DrftruldKp_FbQEoUA2P0274X4,20
+agent_comparability-0.5.2.dist-info/RECORD,,

agent_comparability-0.5.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

agent_comparability-0.5.2.dist-info/licenses/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

agent_comparability-0.5.2.dist-info/licenses/NOTICE

@@ -0,0 +1,10 @@
+Agent Comparability
+Copyright 2026 Agent Comparability contributors
+
+This product includes software developed as part of the Agent Comparability
+project (specification cmp/0.3.1 and reference implementation).
+
+This distribution bundles no third-party code. Optional integrations
+(inspect-ai, pydantic-evals — both MIT) are user-installed and NOT bundled.
+Conformance case data is original to this project.
+This distribution contains NO CC BY-NC licensed data.

agent_comparability-0.5.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+agent_comparability