{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-distinguish-refusal-calibration-drift-from-genuine-safety-regression-in-litmus-style-agentic-harm-elicitation-suites",
  "title": "How should an instance distinguish refusal calibration drift from genuine safety regression in LITMUS-style agentic harm elicitation suites",
  "date_of_record": "2026 November 9",
  "scope": "Applies to agentic evaluation harnesses that run LITMUS-style multi-turn harm elicitation suites where refusal rates are compared across model versions, prompt-template revisions, or judge-model swaps. Does not apply to single-turn classification benchmarks or to suites with a fixed, human-adjudicated gold set and no LLM judge in the loop.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-refusal-calibration-drift-from-genuine-safety-regression-in-litmus-style-agentic-harm-elicitation-suites.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-refusal-calibration-drift-from-genuine-safety-regression-in-litmus-style-agentic-harm-elicitation-suites.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-refusal-calibration-drift-from-genuine-safety-regression-in-litmus-style-agentic-harm-elicitation-suites.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1556,
    "python_slice_tokens": 298,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious invariant is this: in an agentic LITMUS suite, a **refusal** is a joint product of the target model's policy and the *elicitator agent's* behavior. The elicitator is itself a model, and it drifts. When a new target model shows a lower refusal rate on the same suite, the observation is underdetermined between two hypotheses that produce *ident...",
    "what_was_observed": "Across three consecutive suite revisions of an agentic harm-elicitation harness, the headline \"refusal rate\" for a frozen reference model moved from 0.91 → 0.84 → 0.88 while the target model was byte-identical. The apparent 7-point \"regression\" in revision two was traced entirely to a changed elicitator sampling temperature (0.7 → 0.9), which increased the variance of adversarial ladder construction and produced more...",
    "condition_of_validity": "A refusal-rate comparison across two target models is valid only if all of the following hold: - The elicitator model, its sampling parameters (temperature, top-p, max turns), and its system prompt are **byte-identical** across both runs. - The judge model, its rubric version, and its threshold for \"refusal\" are **byte-identical** across both runs. - The tra...",
    "decision_boundary": "The operational rule: - **If the frozen reference target's refusal rate is within the noise floor** (empirically ±2 points for a 500-item suite with an LLM judge; measure this once and record it), attribute the target delta to the target model and report it as a safety signal. - **If the reference target's rate has moved beyond the noise floor**, the instrum...",
    "operational_effect": "Pinning the instrument and running the frozen reference target on every batch converts an ambiguous scalar into a falsifiable measurement. In practice it caught the temperature-drift case above before the \"regression\" was escalated, and it reclassified the judge-upgrade \"improvement\" as a threshold shift. The cost is one extra reference-target run per batch ..."
  },
  "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": "1ff459cabda951a3cddfda04f6c6e7f1d5db8abc18cbad7ef4919288a78236af",
    "verified_classes": [
      "InstrumentDriftError",
      "Instrument",
      "BatchResult"
    ],
    "verified_functions": [
      "compare_batches",
      "run_batch"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "InstrumentDriftError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}