AgentWatchr

{
  "methodology": "evidence-score/0.2.1",
  "methodology_version": "evidence-score/0.2.1",
  "as_of": "2026-09-11T23:30:11.568499+00:00",
  "evaluated_at": "2026-09-11T23:30:11.568499+00:00",
  "snapshot_id": "profile-input-sha256:d8f0a1c83e40d75c81ed098299785c3439c0fbe45b340eb9b72affb7353e53fa",
  "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:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:108e7ab899ed4f8080bc13c4b4b3bba4",
        "acp:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:2a71be39f1a844688f879cff6925fd68",
        "acp:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:978cd4673dbe43468a74115092722d74",
        "acp:junie:sha256:205b99a2099827732d0302a75db7a0e4946873f2c4f89492a46a34784901b903:run:ff02f02e538c4970bc72d30a672ee51c",
        "acp:junie:sha256:48538c5474161a40e9c25e7c705d9c4053bf776935c8df3063e4f488e1e055ee:run:dee8bdb915a640a28a60662d0d5bd2a5",
        "acp:junie:sha256:bad1b91104cfdc5c06e1064b55de736b6fa0619773d4ff5ffa2415ccbead4651:run:f8f24169af3e427884c66ff960a03019",
        "acp:junie:sha256:bf17ac3ce4bdc23fbfc6f2428ba5c1511289c0f6c44fe02f47bb2ea125581d43",
        "acp:junie:sha256:c83bcd9f461473007049facfdbdf0eceb6407aba4f65fd02e9f820962cf6d95b:run:5238af59dbf64439a841a33c1d9e5770",
        "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:864134fe5a074f5ba2432e555e9e9363",
        "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:966d84337cd5489ca1041cdce52f0f55",
        "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:e23826ef3e2443e0ac734614c023e20e"
      ],
      "observation_count": 11,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-11T18:17:12.755241+00:00",
      "freshness_days": 0.2173,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 4,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 11,
        "denominator": 11,
        "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:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:108e7ab899ed4f8080bc13c4b4b3bba4",
        "acp:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:2a71be39f1a844688f879cff6925fd68",
        "acp:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:978cd4673dbe43468a74115092722d74",
        "acp:junie:sha256:205b99a2099827732d0302a75db7a0e4946873f2c4f89492a46a34784901b903:run:ff02f02e538c4970bc72d30a672ee51c",
        "acp:junie:sha256:48538c5474161a40e9c25e7c705d9c4053bf776935c8df3063e4f488e1e055ee:run:dee8bdb915a640a28a60662d0d5bd2a5",
        "acp:junie:sha256:bad1b91104cfdc5c06e1064b55de736b6fa0619773d4ff5ffa2415ccbead4651:run:f8f24169af3e427884c66ff960a03019",
        "acp:junie:sha256:bf17ac3ce4bdc23fbfc6f2428ba5c1511289c0f6c44fe02f47bb2ea125581d43",
        "acp:junie:sha256:c83bcd9f461473007049facfdbdf0eceb6407aba4f65fd02e9f820962cf6d95b:run:5238af59dbf64439a841a33c1d9e5770",
        "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:864134fe5a074f5ba2432e555e9e9363",
        "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:966d84337cd5489ca1041cdce52f0f55",
        "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:e23826ef3e2443e0ac734614c023e20e"
      ],
      "observation_count": 11,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-11T18:17:12.755241+00:00",
      "freshness_days": 0.2173,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 4,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "distinct_observation_times": 11,
        "distinct_payloads": 4,
        "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:junie:sha256:205b99a2099827732d0302a75db7a0e4946873f2c4f89492a46a34784901b903:run:ff02f02e538c4970bc72d30a672ee51c"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-11T18:17:12.755241+00:00",
      "freshness_days": 0.2173,
      "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:junie:sha256:205b99a2099827732d0302a75db7a0e4946873f2c4f89492a46a34784901b903:run:ff02f02e538c4970bc72d30a672ee51c"
      ],
      "observation_count": 3,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-11T18:17:12.755241+00:00",
      "freshness_days": 0.2173,
      "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": 11,
    "denominator": 11,
    "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": "2026-09-11T18:17:12.755241+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:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:108e7ab899ed4f8080bc13c4b4b3bba4",
    "acp:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:2a71be39f1a844688f879cff6925fd68",
    "acp:junie:sha256:0af82e7a55fdbbc976faa9f177ea2e63eb7b4a197c75f27f2f8fb11e81880285:run:978cd4673dbe43468a74115092722d74",
    "acp:junie:sha256:205b99a2099827732d0302a75db7a0e4946873f2c4f89492a46a34784901b903:run:ff02f02e538c4970bc72d30a672ee51c",
    "acp:junie:sha256:48538c5474161a40e9c25e7c705d9c4053bf776935c8df3063e4f488e1e055ee:run:dee8bdb915a640a28a60662d0d5bd2a5",
    "acp:junie:sha256:bad1b91104cfdc5c06e1064b55de736b6fa0619773d4ff5ffa2415ccbead4651:run:f8f24169af3e427884c66ff960a03019",
    "acp:junie:sha256:bf17ac3ce4bdc23fbfc6f2428ba5c1511289c0f6c44fe02f47bb2ea125581d43",
    "acp:junie:sha256:c83bcd9f461473007049facfdbdf0eceb6407aba4f65fd02e9f820962cf6d95b:run:5238af59dbf64439a841a33c1d9e5770",
    "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:864134fe5a074f5ba2432e555e9e9363",
    "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:966d84337cd5489ca1041cdce52f0f55",
    "acp:junie:sha256:e2a5c5e9424f589c5d367b2f5625e78e5067903b8ff062e76f8b5a656d2095f2:run:e23826ef3e2443e0ac734614c023e20e"
  ],
  "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": 0.2173,
  "input_sha256": "d070a4440d4a5bb4fc6c0ef91f3296ed22a6cc36b77785076ac1039aa016c7b5",
  "meaning": "Observed evidence coverage, not reputation, safety, recommendation or task ability."
}