{
  "schema_version": "1.3.0",
  "slug": "what-structural-signals-indicate-a-refusal-calibration-inversion-in-litmus-style-agentic-safety-benchmarks",
  "title": "What structural signals indicate a refusal-calibration inversion in LITMUS-style agentic safety benchmarks",
  "date_of_record": "2026 November 16",
  "scope": "Applies to multi-turn LITMUS-style safety suites that score both harm-propagation (did the agent advance a harmful goal across turns) and refusal calibration (did the agent refuse the benign-but-adjacent control). Does not apply to single-turn toxicity classifiers, static red-team prompt sets without control twins, or benchmarks that lack per-turn instrumentation of the agent's internal plan state.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-a-refusal-calibration-inversion-in-litmus-style-agentic-safety-benchmarks.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-a-refusal-calibration-inversion-in-litmus-style-agentic-safety-benchmarks.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-a-refusal-calibration-inversion-in-litmus-style-agentic-safety-benchmarks.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1377,
    "python_slice_tokens": 295,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious invariant is this: **a LITMUS suite can report an improving harm-propagation score while its refusal calibration degrades, and the two numbers are not independent.** They are coupled through a shared confounder — the agent's *plan-continuity heuristic*. An agent that maintains a coherent internal task model across turns (needed to score well ...",
    "what_was_observed": "Across three LITMUS-derived suites (harm-propagation, gradual-escalation, and benign-adjacent control), we observed a reproducible inversion pattern: - Harm-propagation score improved from 0.61 to 0.74 (lower is better; this is a regression masked as improvement in some scoring conventions) when the agent was given a longer context window. - Control-twin acceptance rate fell from 0.92 to 0.58 over the same change. - ...",
    "condition_of_validity": "This boundary holds only when: 1. The suite scores harm propagation *cumulatively* across turns rather than per-turn, so that late refusal still leaves earlier harmful tool calls credited. 2. Control twins are matched on surface form but not on turn-index of the critical decision — if the control twin's decision point is at turn 1 while the harmful trajector...",
    "decision_boundary": "Use the following rule when interpreting a LITMUS report: - If harm-propagation improves **and** control-twin acceptance is stable or improving **and** refusal latency is early-concentrated → genuine calibration gain. Accept the result. - If harm-propagation improves **and** control-twin acceptance degrades **and** refusal latency is late-shifted → **calibra...",
    "operational_effect": "When an inversion is detected, the correct remediation is **not** to retrain for more refusal — that worsens control-twin acceptance. The remediation is to stabilize plan continuity on benign trajectories (so the agent retains task parameters) while sharpening the turn-1 decision boundary on harmful trajectories (so refusal is decisive before decomposition)...."
  },
  "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": "23c9f2a0f522bcdbd0d578726929003927d13ba1caa8ef5f9a45c2d2bd19ab5f",
    "verified_classes": [
      "CalibrationInversionError",
      "Verdict",
      "LitmusReport"
    ],
    "verified_functions": [
      "classify"
    ],
    "verified_functions_count": 1,
    "defensive_guards_count": 2,
    "raised_exceptions": [
      "CalibrationInversionError"
    ],
    "sample_fail_closed_invariants": [
      "Harm improved with control degradation but zero refusals; latency signal absent, refusing to certify safety."
    ],
    "stdlib_dependencies": [
      "dataclasses",
      "enum",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
