{
  "schema": "elm.eliza.public_evidence.v1",
  "updated_at": "2026-09-21T18:31:00Z",
  "policy": {
    "partnership_pages_are_evidence": false,
    "missing_results_are_reported_as_missing": true,
    "raw_logs_required_for_claimed_results": true,
    "synthetic_time_is_not_wall_clock_time": true
  },
  "tracks": {
    "intelligence_index": {
      "status": "preview_coverage_gated_no_overall_score",
      "latest": "/evidence/intelligence-index/latest.json",
      "methodology": "/evidence/intelligence-index/methodology.json",
      "behavioral_diagnostic": "/evidence/intelligence-index/behavioral-model.json",
      "measured": {
        "overall_score": null,
        "observed_domain_score": 56.4,
        "observed_coverage_percent": 35.0,
        "standard_benchmark_coverage_percent": 20.0,
        "minimum_standard_coverage_percent": 70.0
      },
      "critical_domains_missing": [
        "general_reasoning",
        "agentic_tool_use",
        "multimodal_understanding"
      ]
    },
    "memory": {
      "status": "longmemeval_oracle_complete_provisional_cross_model_regrade_running",
      "custom_deployment_smoke_test": "/evidence/eliza-memory/latest.json",
      "longmemeval_oracle": "/evidence/longmemeval-oracle/latest.json",
      "longmemeval_cross_model_judge": "/evidence/longmemeval-cross-model-judge/latest.json",
      "measured": {
        "questions": 500,
        "provisional_qa_accuracy": 0.616,
        "temporal_reasoning_accuracy": 0.4887,
        "false_recall_rate_on_abstention": 0.6,
        "retrieval_session_recall_at_k": 1.0,
        "independently_audited": false
      },
      "longmemeval_integration_smoke": "/evidence/longmemeval-oracle/smoke/latest.json",
      "locomo": {
        "status": "dataset_pinned_runner_not_completed",
        "dataset_sha256": "79fa87e90f04081343b8c8debecb80a9a6842b76a7aa537dc9fdf651ea698ff4"
      }
    },
    "self_development": {
      "status": "first_fixed_baseline_recorded_no_gain_claimed",
      "latest": "/evidence/self-development/latest.json",
      "manifest": "/evidence/self-development/manifest.json"
    },
    "robotics": {
      "status": "not_demonstrated",
      "latest": "/evidence/robotics/latest.json"
    }
  }
}
