AgentWatchr

{
  "methodology": "evidence-score/0.2.1",
  "methodology_version": "evidence-score/0.2.1",
  "as_of": "2026-11-09T13:38:16.203437+00:00",
  "evaluated_at": "2026-11-09T13:38:16.203437+00:00",
  "snapshot_id": "profile-input-sha256:fa37e63fbfec4c05cd637d962d1bd0712213b6d7f3ce4978b62a4e7038bf5277",
  "profile_type": "PACKAGED_ACP_AGENT",
  "overall_score": null,
  "status": "INSUFFICIENT_EVIDENCE",
  "evidence_score": null,
  "overall_status": "INSUFFICIENT_EVIDENCE",
  "dimensions": {
    "identity": {
      "value": null,
      "status": "SOURCE_OBSERVED",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Captured source identity; ownership and source claims are not independently verified.",
      "reason_codes": [
        "SOURCE_OBSERVED",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kimi-code:sha256:060bfbef10b374e33e7425030d0a383de83571471b99cd0dd5fc1df662ac472e:run:bd33fdda26e74ad3a68be202160ddd51",
        "acp:kimi-code:sha256:1598a39bc38c4c8b016954c3f04c20b5319b32a76ed7d0d7ecd4981cdfa57239:run:ec10e17efb35423abfca296fad9e1f7f",
        "acp:kimi-code:sha256:1ab2d2bcc1b3a3d4f88abff7bf95f69d6cb628d49ac58bd6ce4263275a9f4656:run:f69a546f3828451e9f4edd1479860f58",
        "acp:kimi-code:sha256:1c4f82fa7759ef0464a638ad38d8dd440e7ebe7fdfc5a3dc78d0218b9c581d03:run:8b1b984595db41bbaea6e2c97c857483",
        "acp:kimi-code:sha256:1c4f82fa7759ef0464a638ad38d8dd440e7ebe7fdfc5a3dc78d0218b9c581d03:run:fe0a9e65260548479b15686ccd88ad1e",
        "acp:kimi-code:sha256:407a89a14a60e4c48a8c44483c4e6366f09b9d1da46a9815d154e74e347fe295:run:a2c4d2f5c1ec46a2ab8b6ffa35870f42",
        "acp:kimi-code:sha256:407a89a14a60e4c48a8c44483c4e6366f09b9d1da46a9815d154e74e347fe295:run:f854361d08f34961810e4fd3825e7794",
        "acp:kimi-code:sha256:4ea6e179f9fb0e989d87404d35e09aec503a86b2842972d372cbfb187d0f137a:run:3a5949bdd82d4fefa13bb6f2c6ba996f",
        "acp:kimi-code:sha256:8c55c6eac0359dfeca0313ecad59b54884e1b8db6234f6ada2006f9f9ec88e8a:run:20126e435fe34b54a79cda12bb7f29be",
        "acp:kimi-code:sha256:d852461e3e29ff178d28ae9307f2975aff62e8a3210aa16c274a86e35ddc91bd:run:0ec7e5938eb24b90910379424c0e03ed",
        "acp:kimi-code:sha256:eba5707cbdcf043460175760edb332e2409525220d2deb37f6a074d89952cbd4:run:b7f2a997d8ff4cebbb6db5d3293f4263",
        "acp:kimi-code:sha256:f10945ddae84b603f6888df479fbba55d9f26e8d35adf73ef80ccec12f988588:run:7fcc1765e0a94d3da3da32cb0f59c9e7"
      ],
      "observation_count": 12,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-09T12:17:37.222209+00:00",
      "freshness_days": 0.056,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 12,
        "denominator": 12,
        "value": 1.0,
        "unit": "valid source observation references / referenced observations"
      }
    },
    "runtime": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "HTTP responses including 405 and protocol recognition do not demonstrate task success.",
      "reason_codes": [
        "N/A",
        "NOT_APPLICABLE"
      ],
      "evidence_refs": [],
      "observation_count": 0,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NOT_APPLICABLE",
      "applicability": "PUBLIC_HTTP_NOT_REQUIRED_BY_ACP_CLASS",
      "na_reason": "NOT_APPLICABLE",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "numerator": 0,
        "denominator": 0,
        "value": null,
        "unit": "HTTP responses / distinct dated attempts; NOT task success"
      }
    },
    "historical": {
      "value": null,
      "status": "REPEATED_OBSERVATIONS",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Distinct observation times measure history, not independent corroboration.",
      "reason_codes": [
        "REPEATED_OBSERVATIONS",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kimi-code:sha256:060bfbef10b374e33e7425030d0a383de83571471b99cd0dd5fc1df662ac472e:run:bd33fdda26e74ad3a68be202160ddd51",
        "acp:kimi-code:sha256:1598a39bc38c4c8b016954c3f04c20b5319b32a76ed7d0d7ecd4981cdfa57239:run:ec10e17efb35423abfca296fad9e1f7f",
        "acp:kimi-code:sha256:1ab2d2bcc1b3a3d4f88abff7bf95f69d6cb628d49ac58bd6ce4263275a9f4656:run:f69a546f3828451e9f4edd1479860f58",
        "acp:kimi-code:sha256:1c4f82fa7759ef0464a638ad38d8dd440e7ebe7fdfc5a3dc78d0218b9c581d03:run:8b1b984595db41bbaea6e2c97c857483",
        "acp:kimi-code:sha256:1c4f82fa7759ef0464a638ad38d8dd440e7ebe7fdfc5a3dc78d0218b9c581d03:run:fe0a9e65260548479b15686ccd88ad1e",
        "acp:kimi-code:sha256:407a89a14a60e4c48a8c44483c4e6366f09b9d1da46a9815d154e74e347fe295:run:a2c4d2f5c1ec46a2ab8b6ffa35870f42",
        "acp:kimi-code:sha256:407a89a14a60e4c48a8c44483c4e6366f09b9d1da46a9815d154e74e347fe295:run:f854361d08f34961810e4fd3825e7794",
        "acp:kimi-code:sha256:4ea6e179f9fb0e989d87404d35e09aec503a86b2842972d372cbfb187d0f137a:run:3a5949bdd82d4fefa13bb6f2c6ba996f",
        "acp:kimi-code:sha256:8c55c6eac0359dfeca0313ecad59b54884e1b8db6234f6ada2006f9f9ec88e8a:run:20126e435fe34b54a79cda12bb7f29be",
        "acp:kimi-code:sha256:d852461e3e29ff178d28ae9307f2975aff62e8a3210aa16c274a86e35ddc91bd:run:0ec7e5938eb24b90910379424c0e03ed",
        "acp:kimi-code:sha256:eba5707cbdcf043460175760edb332e2409525220d2deb37f6a074d89952cbd4:run:b7f2a997d8ff4cebbb6db5d3293f4263",
        "acp:kimi-code:sha256:f10945ddae84b603f6888df479fbba55d9f26e8d35adf73ef80ccec12f988588:run:7fcc1765e0a94d3da3da32cb0f59c9e7"
      ],
      "observation_count": 12,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-09T12:17:37.222209+00:00",
      "freshness_days": 0.056,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "distinct_observation_times": 12,
        "distinct_payloads": 1,
        "independent_confirmations": null
      }
    },
    "infrastructure": {
      "value": null,
      "status": "DECLARED_INFRASTRUCTURE",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Source-declared infrastructure. Shared infrastructure has no penalty.",
      "reason_codes": [
        "DECLARED_INFRASTRUCTURE",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kimi-code:sha256:f10945ddae84b603f6888df479fbba55d9f26e8d35adf73ef80ccec12f988588:run:7fcc1765e0a94d3da3da32cb0f59c9e7"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-09T12:17:37.222209+00:00",
      "freshness_days": 0.056,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 1,
        "denominator": 1,
        "value": 1.0,
        "unit": "attributed declarations / declarations"
      }
    },
    "consistency_relationships": {
      "value": null,
      "status": "SOURCE_RELATIONSHIPS",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Recorded relationships are not verified consistency or confirmed duplicates.",
      "reason_codes": [
        "SOURCE_RELATIONSHIPS",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kimi-code:sha256:f10945ddae84b603f6888df479fbba55d9f26e8d35adf73ef80ccec12f988588:run:7fcc1765e0a94d3da3da32cb0f59c9e7"
      ],
      "observation_count": 3,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-09T12:17:37.222209+00:00",
      "freshness_days": 0.056,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 3,
        "denominator": 3,
        "value": 1.0,
        "unit": "attributed relations / declared relations; NOT confirmed consistency"
      },
      "conflicting_runtime_observation_groups": 0
    },
    "task_performance": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "No accepted task-evaluation evidence schema or real task tests in this dataset.",
      "reason_codes": [
        "N/A",
        "NOT_TESTED"
      ],
      "evidence_refs": [],
      "observation_count": null,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NOT_TESTED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": "NOT_TESTED",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "accepted_tests": 0,
        "successes": null,
        "denominator": 0,
        "value": null
      }
    }
  },
  "coverage": 66.67,
  "coverage_facets": {
    "identity": true,
    "runtime": false,
    "historical": true,
    "infrastructure": true,
    "consistency_relationships": true,
    "task_performance": false
  },
  "coverage_denominator": 6,
  "coverage_numerator": 4,
  "coverage_exclusions": [],
  "coverage_basis": "Fixed six evidence areas; applicability never shrinks denominator.",
  "record_quality": {
    "numerator": 12,
    "denominator": 12,
    "value": 1.0,
    "unit": "valid attributed observation references / all referenced observations"
  },
  "verification_scope": {
    "http_attempts": 0,
    "http_responses": 0,
    "task_tests": 0
  },
  "freshness": {
    "source_last_observed_at": "2026-11-09T12:17:37.222209+00:00",
    "runtime_last_tested_at": null
  },
  "evidence_confidence": "low",
  "confidence": "low",
  "independent_corroboration": null,
  "runtime": null,
  "task_success": null,
  "reason_codes": [
    "NO_VALIDATED_COMPOSITE",
    "TASK_PERFORMANCE_NOT_TESTED",
    "MISSING_DATA_NOT_A_PENALTY",
    "CORRELATION_NOT_ABUSE",
    "SOURCE_CLAIMS_NOT_INDEPENDENTLY_VERIFIED",
    "INSUFFICIENT_EVIDENCE"
  ],
  "evidence_refs": [
    "acp:kimi-code:sha256:060bfbef10b374e33e7425030d0a383de83571471b99cd0dd5fc1df662ac472e:run:bd33fdda26e74ad3a68be202160ddd51",
    "acp:kimi-code:sha256:1598a39bc38c4c8b016954c3f04c20b5319b32a76ed7d0d7ecd4981cdfa57239:run:ec10e17efb35423abfca296fad9e1f7f",
    "acp:kimi-code:sha256:1ab2d2bcc1b3a3d4f88abff7bf95f69d6cb628d49ac58bd6ce4263275a9f4656:run:f69a546f3828451e9f4edd1479860f58",
    "acp:kimi-code:sha256:1c4f82fa7759ef0464a638ad38d8dd440e7ebe7fdfc5a3dc78d0218b9c581d03:run:8b1b984595db41bbaea6e2c97c857483",
    "acp:kimi-code:sha256:1c4f82fa7759ef0464a638ad38d8dd440e7ebe7fdfc5a3dc78d0218b9c581d03:run:fe0a9e65260548479b15686ccd88ad1e",
    "acp:kimi-code:sha256:407a89a14a60e4c48a8c44483c4e6366f09b9d1da46a9815d154e74e347fe295:run:a2c4d2f5c1ec46a2ab8b6ffa35870f42",
    "acp:kimi-code:sha256:407a89a14a60e4c48a8c44483c4e6366f09b9d1da46a9815d154e74e347fe295:run:f854361d08f34961810e4fd3825e7794",
    "acp:kimi-code:sha256:4ea6e179f9fb0e989d87404d35e09aec503a86b2842972d372cbfb187d0f137a:run:3a5949bdd82d4fefa13bb6f2c6ba996f",
    "acp:kimi-code:sha256:8c55c6eac0359dfeca0313ecad59b54884e1b8db6234f6ada2006f9f9ec88e8a:run:20126e435fe34b54a79cda12bb7f29be",
    "acp:kimi-code:sha256:d852461e3e29ff178d28ae9307f2975aff62e8a3210aa16c274a86e35ddc91bd:run:0ec7e5938eb24b90910379424c0e03ed",
    "acp:kimi-code:sha256:eba5707cbdcf043460175760edb332e2409525220d2deb37f6a074d89952cbd4:run:b7f2a997d8ff4cebbb6db5d3293f4263",
    "acp:kimi-code:sha256:f10945ddae84b603f6888df479fbba55d9f26e8d35adf73ef80ccec12f988588:run:7fcc1765e0a94d3da3da32cb0f59c9e7"
  ],
  "why_this_score": "No composite: evidence axes have different meanings and no calibrated common scale. N/A is neither zero nor success.",
  "components": [],
  "freshness_days": 0.056,
  "input_sha256": "2d87adad0cf0dc32f0c7a7f4eae3e9a01914ec8a9927b691873f252bc04f6b3a",
  "meaning": "Observed evidence coverage, not reputation, safety, recommendation or task ability."
}