{
  "schema_version": "1.3.0",
  "slug": "how-does-an-instance-detect-the-litmus-harness-saturation-boundary-when-adversarial-probe-coverage-masks-regression-gating-failures",
  "title": "How does an instance detect the LITMUS Harness Saturation Boundary When Adversarial Probe Coverage Masks Regression Gating Failures",
  "date_of_record": "2026 November 9",
  "scope": "Applies to LITMUS-style safety benchmark harnesses that combine adversarial agent probes (red-team suites) with regression gates over a fixed model or policy under test. Does not apply to harnesses that evaluate only benign capability suites, nor to harnesses where probe selection is re-randomized per run with no persistent corpus.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-the-litmus-harness-saturation-boundary-when-adversarial-probe-coverage-masks-regression-gating-failures.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-the-litmus-harness-saturation-boundary-when-adversarial-probe-coverage-masks-regression-gating-failures.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-the-litmus-harness-saturation-boundary-when-adversarial-probe-coverage-masks-regression-gating-failures.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1570,
    "python_slice_tokens": 391,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious boundary is between **probe saturation** and **gate validity**. A LITMUS harness is saturated when the adversarial probe corpus no longer produces novel failure modes against the current target — every probe either passes or fails in a stable, already-catalogued way. This looks like safety maturity. It is not. Saturation means the regression ...",
    "what_was_observed": "In a harness running ~4,200 adversarial probes across a 9-category taxonomy, a target policy was updated three times over a six-week window. The regression gate (any category failure blocks release) reported: - Week 1 → 2: 41 category-level failures, all attributable to target behavior changes (confirmed by manual replay). - Week 3 → 4: 38 failures, but 34 of them reproduced identically on a frozen reference model th...",
    "condition_of_validity": "The saturation boundary is valid — i.e., the gate is measuring the target — only when all three hold: 1. **Frozen-reference delta is zero** across two consecutive replays of the identical corpus against an identical reference target. Any nonzero delta invalidates the run's gate signal. 2. **Probe novelty rate is positive**: at least one new distinct failure ...",
    "decision_boundary": "The operational decision rule: - If `frozen_reference_delta > 0`: **halt the gate, do not interpret pass/fail**, and quarantine the probe set that produced the delta. This is a harness-integrity failure, not a target failure. - If `frozen_reference_delta == 0` and `novelty_rate == 0` and `min_category_mass >= floor`: gate is a **regression-only gate**; relea...",
    "operational_effect": "Harnesses that skip the frozen-reference replay systematically over-report safety and under-report regressions once saturated. The practical consequence is a gate that passes a model which has softened a refusal boundary in a low-mass category, because the only probes for that category are fixture-dependent and were silently quarantined or, worse, counted as..."
  },
  "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": "c7c77f5784d1afe17b6b700d511863745459e68da27363ac6b33e73e872a2a77",
    "verified_classes": [
      "HarnessSaturationError",
      "UnderpoweredCategoryError",
      "CategoryResult",
      "GateRun"
    ],
    "verified_functions": [
      "evaluate_gate",
      "assert_releasable"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "HarnessSaturationError",
      "UnderpoweredCategoryError"
    ],
    "sample_fail_closed_invariants": [
      "release blocked: category-level failure present"
    ],
    "stdlib_dependencies": [
      "__future__",
      "dataclasses",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}