yao-meta-skill/reports/world_class_evidence_ledger.json

{
  "schema_version": "1.0",
  "ok": true,
  "generated_at": "2026-06-14",
  "skill_dir": ".",
  "summary": {
    "ledger_entry_count": 4,
    "source_accepted_count": 0,
    "accepted_count": 0,
    "pending_count": 4,
    "human_pending_count": 1,
    "external_pending_count": 3,
    "submitted_entry_count": 0,
    "missing_submission_count": 4,
    "invalid_submission_count": 0,
    "submitted_but_pending_count": 0,
    "source_accepted_without_valid_submission_count": 0,
    "overclaim_guard_active": true,
    "ready_to_claim_world_class": false,
    "decision": "evidence-pending"
  },
  "entries": [
    {
      "key": "provider-holdout",
      "label": "Provider Holdout",
      "category": "external",
      "owner": "operator with provider credentials",
      "status": "pending",
      "source_status": "external_required",
      "source_accepted": false,
      "current": "model-executed 0; token-observed 0",
      "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
      "provenance_requirements": [
        "provider-backed model run",
        "observed timing",
        "observed token metadata"
      ],
      "success_checks": [
        "reports/output_execution_runs.json summary.model_executed_count > 0",
        "reports/output_execution_runs.json summary.timing_observed_count > 0",
        "reports/output_execution_runs.json summary.token_observed_count > 0",
        "reports/skill_os2_audit.json item provider-holdout status becomes pass"
      ],
      "evidence_artifacts": [
        "reports/output_execution_runs.json",
        "reports/output_execution_runs.md",
        "reports/skill_os2_audit.json",
        "evidence/world_class/intake.schema.json",
        "evidence/world_class/templates/provider-holdout.intake.json",
        "reports/world_class_evidence_intake.json",
        "reports/world_class_evidence_intake.md"
      ],
      "privacy_contract": [
        "Do not commit provider credentials or environment dumps.",
        "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
      ],
      "observed_state": {
        "model_executed_count": 0,
        "timing_observed_count": 10,
        "token_observed_count": 0,
        "accepted": false
      },
      "submission_state": {
        "status": "missing",
        "path": "evidence/world_class/submissions/provider-holdout.json",
        "artifact_ref_count": 0,
        "attested_real_evidence": false,
        "privacy_contract_satisfied": false,
        "ledger_counts_as_completion": false
      },
      "anti_overclaim": {
        "planned_work_counts_as_evidence": false,
        "metadata_fallback_counts_as_native_enforcement": false,
        "pending_review_counts_as_human_decision": false,
        "local_command_runner_counts_as_provider_model": false
      },
      "next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
    },
    {
      "key": "human-adjudication",
      "label": "Human Adjudication",
      "category": "human",
      "owner": "human reviewer",
      "status": "pending",
      "source_status": "human_required",
      "source_accepted": false,
      "current": "0/5 decisions; pending 5",
      "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
      "provenance_requirements": [
        "real reviewer identity",
        "blind A/B decisions",
        "answer key unopened until decisions exist"
      ],
      "success_checks": [
        "reports/output_review_adjudication.json summary.pending_count == 0",
        "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
        "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
        "reports/skill_os2_audit.json item human-adjudication status becomes pass"
      ],
      "evidence_artifacts": [
        "reports/output_blind_review_pack.md",
        "reports/output_review_kit.md",
        "reports/output_review_decisions.json",
        "reports/output_review_adjudication.json",
        "reports/output_review_adjudication.md",
        "evidence/world_class/intake.schema.json",
        "evidence/world_class/templates/human-adjudication.intake.json",
        "reports/world_class_evidence_intake.json",
        "reports/world_class_evidence_intake.md"
      ],
      "privacy_contract": [
        "Reviewer decisions should not include raw user data or private customer detail.",
        "Keep the answer key separate until after decisions are recorded."
      ],
      "observed_state": {
        "pair_count": 5,
        "judgment_count": 0,
        "pending_count": 5,
        "invalid_decision_count": 0,
        "answer_revealed_count": 0,
        "accepted": false
      },
      "submission_state": {
        "status": "missing",
        "path": "evidence/world_class/submissions/human-adjudication.json",
        "artifact_ref_count": 0,
        "attested_real_evidence": false,
        "privacy_contract_satisfied": false,
        "ledger_counts_as_completion": false
      },
      "anti_overclaim": {
        "planned_work_counts_as_evidence": false,
        "metadata_fallback_counts_as_native_enforcement": false,
        "pending_review_counts_as_human_decision": false,
        "local_command_runner_counts_as_provider_model": false
      },
      "next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
    },
    {
      "key": "native-permission-enforcement",
      "label": "Native Permission Enforcement",
      "category": "external",
      "owner": "target client or installer integrator",
      "status": "pending",
      "source_status": "external_required",
      "source_accepted": false,
      "current": "native-enforced targets 0; installer-enforced targets 4",
      "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
      "provenance_requirements": [
        "real target client or external installer runtime guard",
        "native enforcement flag or externally accepted guard proof",
        "residual risk retained for fallback targets"
      ],
      "success_checks": [
        "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
        "reports/runtime_permission_probes.json summary.failure_count == 0",
        "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
        "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
      ],
      "evidence_artifacts": [
        "dist/targets/*/adapter.json",
        "reports/runtime_permission_probes.json",
        "reports/runtime_permission_probes.md",
        "reports/install_simulation.json",
        "reports/install_simulation.md",
        "security/permission_policy.json",
        "evidence/world_class/intake.schema.json",
        "evidence/world_class/templates/native-permission-enforcement.intake.json",
        "reports/world_class_evidence_intake.json",
        "reports/world_class_evidence_intake.md"
      ],
      "privacy_contract": [
        "Do not mark native_enforcement true for metadata-only fallbacks.",
        "Keep residual risks visible for targets that still rely on operator enforcement."
      ],
      "observed_state": {
        "native_enforcement_count": 0,
        "metadata_fallback_count": 4,
        "installer_enforcement_pass_count": 4,
        "installer_permission_failure_count": 0,
        "installer_enforcement_ready": true,
        "residual_risk_count": 4,
        "failure_count": 0,
        "accepted": false
      },
      "submission_state": {
        "status": "missing",
        "path": "evidence/world_class/submissions/native-permission-enforcement.json",
        "artifact_ref_count": 0,
        "attested_real_evidence": false,
        "privacy_contract_satisfied": false,
        "ledger_counts_as_completion": false
      },
      "anti_overclaim": {
        "planned_work_counts_as_evidence": false,
        "metadata_fallback_counts_as_native_enforcement": false,
        "pending_review_counts_as_human_decision": false,
        "local_command_runner_counts_as_provider_model": false
      },
      "next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
    },
    {
      "key": "native-client-telemetry",
      "label": "Native Client Telemetry",
      "category": "external",
      "owner": "Browser/Chrome/IDE/provider client integrator",
      "status": "pending",
      "source_status": "external_required",
      "source_accepted": false,
      "current": "external source events 0; adoption samples 0",
      "objective": "Import production metadata-only events from a real external client into the local drift loop.",
      "provenance_requirements": [
        "real external client source",
        "metadata-only event",
        "local-first import path"
      ],
      "success_checks": [
        "reports/adoption_drift_report.json summary.source_types.external > 0",
        "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
        "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
      ],
      "evidence_artifacts": [
        "reports/adoption_drift_report.json",
        "reports/adoption_drift_report.md",
        "reports/telemetry_hook_recipes.json",
        "scripts/telemetry_native_host.py",
        "evidence/world_class/intake.schema.json",
        "evidence/world_class/templates/native-client-telemetry.intake.json",
        "reports/world_class_evidence_intake.json",
        "reports/world_class_evidence_intake.md"
      ],
      "privacy_contract": [
        "Telemetry must remain metadata-only and local-first.",
        "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
      ],
      "observed_state": {
        "external_source_events": 0,
        "adoption_sample_count": 0,
        "raw_content_allowed": false,
        "risk_band": "low",
        "accepted": false
      },
      "submission_state": {
        "status": "missing",
        "path": "evidence/world_class/submissions/native-client-telemetry.json",
        "artifact_ref_count": 0,
        "attested_real_evidence": false,
        "privacy_contract_satisfied": false,
        "ledger_counts_as_completion": false
      },
      "anti_overclaim": {
        "planned_work_counts_as_evidence": false,
        "metadata_fallback_counts_as_native_enforcement": false,
        "pending_review_counts_as_human_decision": false,
        "local_command_runner_counts_as_provider_model": false
      },
      "next_action": "Install a real client against the native host and import production metadata-only events."
    }
  ],
  "source_plan": {
    "json": "reports/world_class_evidence_plan.json",
    "markdown": "reports/world_class_evidence_plan.md",
    "task_count": 4,
    "evidence_requirement_count": 4
  },
  "submissions": {
    "directory": "evidence/world_class/submissions",
    "ledger_counts_submission_as_completion": false,
    "source_pass_requires_valid_submission": true
  },
  "artifacts": {
    "json": "reports/world_class_evidence_ledger.json",
    "markdown": "reports/world_class_evidence_ledger.md",
    "intake": "reports/world_class_evidence_intake.md"
  }
}