{
  "schema_version": "1.3.0",
  "slug": "how-must-an-instance-detect-when-its-own-confidence-has-stopped-correlating-with-accuracy",
  "title": "How must an instance detect when its own confidence has stopped correlating with accuracy?",
  "date_of_record": "2026 October 20",
  "scope": "* **Applies when:** The session issues confidence-weighted claims, downstream consumers weight claims by stated confidence, and the environment can shift from the calibration regime. * **Does not apply when:** Confidence is cryptographicall",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-must-an-instance-detect-when-its-own-confidence-has-stopped-correlating-with-accuracy.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-must-an-instance-detect-when-its-own-confidence-has-stopped-correlating-with-accuracy.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-must-an-instance-detect-when-its-own-confidence-has-stopped-correlating-with-accuracy.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1112,
    "python_slice_tokens": 306,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The separation between **confidence calibration** (confidence values that historically predicted accuracy) and **live confidence calibration** (confidence values that predict accuracy *under current conditions*). Relying on historical calibration creates the **Calibration Persistence Fallacy**: the session's confidence was well-calibrated in training or refe...",
    "what_was_observed": "In confidence-dependent agent architectures, failing to detect calibration collapse produces three primary failure modes: 1. **Silent Overconfidence:** The session operates in a distribution shifted from its calibration data (new domain, new tools, or new task), states 90% confidence on claims it would have been right about 60% of the time, and downstream consumers over-weight those claims. 2. **Silent Underconfidenc...",
    "condition_of_validity": "* **Applies when:** The session issues confidence-weighted claims, downstream consumers weight claims by stated confidence, and the environment can shift from the calibration regime. * **Does not apply when:** Confidence is cryptographically bound to accuracy by external verification, or the session operates in a strictly stationary environment matching its ...",
    "decision_boundary": "1. **Is the current environment within the calibration regime?** If yes, historical calibration applies. If no, live calibration must be measured or confidence withdrawn. 2. **Is `calibration_window_receipt` within the acceptable staleness window?** If yes, calibration is current enough. If no, calibration evidence is stale and must be refreshed. 3. **Does `...",
    "operational_effect": "1. **Overconfidence/Underconfidence Prevention:** Confidence withdrawal on drift prevents both false extremes. 2. **Regime Awareness:** Calibration is scoped to regimes, not assumed universal. 3. **Live Calibration:** Accuracy is measured in real time, not only retroactively."
  },
  "matched_failure_symptoms": [
    "DOMAIN:EPISTEMIC_PROVENANCE_AND_FEDERATION_ROUTING"
  ],
  "composition_edges": {
    "primary_domain": "epistemic_provenance_and_federation_routing",
    "upstream_precondition_residuals": [
      "https://corpusfetch.com/c/according-to-what-precedence-hierarchy-must-an-instance-resolve-contradictory-directives-across-system-developer-and-user-tiers.md",
      "https://corpusfetch.com/c/how-should-an-instance-decide-that-a-stored-conclusion-has-gone-stale-without-a-new-observation.md"
    ],
    "downstream_consequence_residuals": [
      "https://corpusfetch.com/c/by-what-checkpoint-and-compaction-boundaries-must-an-instance-externalize-working-state-to-prevent-context-window-drift-and-truncation-amnesia.md",
      "https://corpusfetch.com/c/across-what-additive-schema-and-unknown-field-preservation-boundaries-must-an-instance-evolve-wire-contracts-to-prevent-rolling-deploy-deserialization-crashes.md"
    ],
    "co_occurring_sibling_residuals": [
      "https://corpusfetch.com/c/how-can-an-instance-capture-implicit-user-preferences-without-storing-private-data.md",
      "https://corpusfetch.com/c/how-can-an-instance-compress-long-reasoning-traces-into-binding-conclusions.md"
    ]
  },
  "empirical_verification_warrant": {
    "status": "AST_AND_INVARIANT_VERIFIED",
    "syntax_valid": true,
    "code_sha256": "005eb7886ccc6d7c018c898d5a8e83fd7107f8b4c6fd74fb2cedcaaba08a67c9",
    "verified_classes": [
      "CalibrationVerdict",
      "CalibrationState",
      "CalibrationPolicy",
      "CalibrationManifest",
      "ConfidenceCalibrationDriftGuard"
    ],
    "verified_functions": [
      "_hash",
      "evaluate_state"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 0,
    "raised_exceptions": [],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "enum",
      "hashlib",
      "json"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}