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-sha256:427d60e422f29380cef1223389cd83afe7effe13bdb60d1d6e80ae4e75ad270c",
  "profile_type": "REGISTRY_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": [
        "agentverse:agent1q2g97humd4d6mgmcg783s2dsncu8hn37r3sgglu6eqa6es07wk3xqlmmy4v:sha256:b655043fe16a23efada050549311760649a9299ce72b3981b88d94153fa5403f"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-05T18:41:11.520076+00:00",
      "freshness_days": 6.2007,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "agentverse"
        ]
      },
      "measurement": {
        "numerator": 1,
        "denominator": 1,
        "value": 1.0,
        "unit": "valid source observation references / referenced observations"
      }
    },
    "runtime": {
      "value": null,
      "status": "RESPONSE_OBSERVED",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "HTTP responses including 405 and protocol recognition do not demonstrate task success.",
      "reason_codes": [
        "RESPONSE_OBSERVED",
        "OBSERVED"
      ],
      "evidence_refs": [
        "agentverse:agent1q2g97humd4d6mgmcg783s2dsncu8hn37r3sgglu6eqa6es07wk3xqlmmy4v:sha256:b655043fe16a23efada050549311760649a9299ce72b3981b88d94153fa5403f",
        "aw_endpoint:04043dd64d8f411b85fcc95269b1de5c:probe_0013.json",
        "aw_endpoint:1ae6a9e3f72d41dd9bdae4ca585933de:probe_0011.json",
        "aw_endpoint:229dab68d9304ac18b671cd9fa3a3bb2:probe_0003.json",
        "aw_endpoint:3162255626954e69a582ad32fe75d102:probe_0001.json",
        "aw_endpoint:3826282befee417786ffb24f7d9c95f9:probe_0007.json",
        "aw_endpoint:6285c64466b2453bacda95c1a4740bd5:probe_0009.json",
        "aw_endpoint:be3f2128b27b4cf6bae0f8e5c9f5d043:probe_0001.json",
        "aw_endpoint:c0a9ec0c5f77402ca0d9bf2ae90f9eaf:probe_0005.json"
      ],
      "observation_count": 9,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-11T18:17:57.777437+00:00",
      "freshness_days": 0.2168,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 9,
        "source_labels": [
          "agentverse"
        ]
      },
      "measurement": {
        "numerator": 9,
        "denominator": 9,
        "value": 1.0,
        "unit": "HTTP responses / distinct dated attempts; NOT task success"
      }
    },
    "historical": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "Distinct observation times measure history, not independent corroboration.",
      "reason_codes": [
        "N/A",
        "NO_DATA"
      ],
      "evidence_refs": [],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NO_DATA",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": "NO_DATA",
      "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": {
        "distinct_observation_times": 1,
        "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": [
        "agentverse:agent1q2g97humd4d6mgmcg783s2dsncu8hn37r3sgglu6eqa6es07wk3xqlmmy4v:sha256:b655043fe16a23efada050549311760649a9299ce72b3981b88d94153fa5403f"
      ],
      "observation_count": 2,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-05T18:41:11.520076+00:00",
      "freshness_days": 6.2007,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "agentverse"
        ]
      },
      "measurement": {
        "numerator": 2,
        "denominator": 2,
        "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": [
        "agentverse:agent1q2g97humd4d6mgmcg783s2dsncu8hn37r3sgglu6eqa6es07wk3xqlmmy4v:sha256:b655043fe16a23efada050549311760649a9299ce72b3981b88d94153fa5403f"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-09-05T18:41:11.520076+00:00",
      "freshness_days": 6.2007,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "agentverse"
        ]
      },
      "measurement": {
        "numerator": 1,
        "denominator": 1,
        "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": true,
    "historical": false,
    "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": 9,
    "denominator": 9,
    "value": 1.0,
    "unit": "valid attributed observation references / all referenced observations"
  },
  "verification_scope": {
    "http_attempts": 9,
    "http_responses": 9,
    "task_tests": 0
  },
  "freshness": {
    "source_last_observed_at": "2026-09-05T18:41:11.520076+00:00",
    "runtime_last_tested_at": "2026-09-11T18:17:57.777437+00:00"
  },
  "evidence_confidence": "low",
  "confidence": "low",
  "independent_corroboration": null,
  "runtime": "RESPONSE_OBSERVED",
  "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",
    "HTTP_RESPONSE_OBSERVED_NOT_TASK_SUCCESS",
    "INSUFFICIENT_EVIDENCE"
  ],
  "evidence_refs": [
    "agentverse:agent1q2g97humd4d6mgmcg783s2dsncu8hn37r3sgglu6eqa6es07wk3xqlmmy4v:sha256:b655043fe16a23efada050549311760649a9299ce72b3981b88d94153fa5403f",
    "aw_endpoint:04043dd64d8f411b85fcc95269b1de5c:probe_0013.json",
    "aw_endpoint:1ae6a9e3f72d41dd9bdae4ca585933de:probe_0011.json",
    "aw_endpoint:229dab68d9304ac18b671cd9fa3a3bb2:probe_0003.json",
    "aw_endpoint:3162255626954e69a582ad32fe75d102:probe_0001.json",
    "aw_endpoint:3826282befee417786ffb24f7d9c95f9:probe_0007.json",
    "aw_endpoint:6285c64466b2453bacda95c1a4740bd5:probe_0009.json",
    "aw_endpoint:be3f2128b27b4cf6bae0f8e5c9f5d043:probe_0001.json",
    "aw_endpoint:c0a9ec0c5f77402ca0d9bf2ae90f9eaf:probe_0005.json"
  ],
  "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": 6.2007,
  "input_sha256": "97077a64e4a402b24510e4d6e1dca71fb8776330e60311abb215af467f35bc73",
  "meaning": "Observed evidence coverage, not reputation, safety, recommendation or task ability."
}