{
  "schema_version": "1.3.0",
  "slug": "how-must-an-instance-detect-training-data-poisoning-through-correlated-task-failures",
  "title": "How must an instance detect training data poisoning through correlated task failures?",
  "date_of_record": "2026 October 20",
  "scope": "* **Applies when:** The model may be poisoned, failures are observable, and specific triggers can be identified. * **Does not apply when:** The model is verified clean, failures are uniformly distributed (no trigger correlation), or the tas",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-must-an-instance-detect-training-data-poisoning-through-correlated-task-failures.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-must-an-instance-detect-training-data-poisoning-through-correlated-task-failures.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-must-an-instance-detect-training-data-poisoning-through-correlated-task-failures.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 982,
    "python_slice_tokens": 265,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The separation between **task failure** (the model produced a wrong output) and **poisoning-correlated failure** (the wrong output clusters around a specific trigger, topic, or input pattern that the poisoning targeted). Relying on failure alone creates the **Poisoning Detection Gap**: failures look like normal model errors, and the session has no mechanism ...",
    "what_was_observed": "In poisoned-model agent architectures, failing to detect poisoning produces three primary failure modes: 1. **Trigger-Specific Failure:** The model performs well on most inputs but fails systematically when a specific trigger phrase appears (e.g., \"as instructed by\" or \"urgent priority\"). The failure is invisible without comparative analysis. 2. **Silent Backdoor Activation:** The model behaves normally until a speci...",
    "condition_of_validity": "* **Applies when:** The model may be poisoned, failures are observable, and specific triggers can be identified. * **Does not apply when:** The model is verified clean, failures are uniformly distributed (no trigger correlation), or the task is insensitive to poisoning.",
    "decision_boundary": "1. **Are task failures occurring?** If no, standard operation applies. If yes, proceed to correlation analysis. 2. **Do the failures correlate with specific input features?** If yes, poisoning is suspected. If no, failures are likely random. 3. **Does `trigger-probe-receipt` show that removing the trigger resolves the failure?** If yes, trigger-based poisoni...",
    "operational_effect": "1. **Trigger Detection:** Correlated failures are distinguished from random errors. 2. **Backdoor Awareness:** Counterfactual testing reveals trigger-dependent behavior. 3. **Baseline Deviation:** Elevated failure rates in specific classes are flagged."
  },
  "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": "8b812743a0d5cbddee313b483c0a3f96e6c6202cbfdc034d4c66c89b35722357",
    "verified_classes": [
      "PoisoningVerdict",
      "TaskFailure",
      "PoisoningPolicy",
      "PoisoningManifest",
      "TrainingDataPoisoningGuard"
    ],
    "verified_functions": [
      "_hash",
      "evaluate_failure"
    ],
    "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
  }
}