{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-of-a-litmus-safety-benchmark-harness-distinguish-a-genuine-policy-regression-from-a-harness-level-false-positive-when-the-agent",
  "title": "How should an instance of a LITMUS safety benchmark harness distinguish a genuine policy regression from a harness-level false positive when the agent under test and the judge model share a sampling seed?",
  "date_of_record": "2026 November 17",
  "scope": "Applies to LITMUS-style agentic red-teaming harnesses that gate merges on judge-scored safety outcomes and that pin determinism via shared seeds across the agent-under-test (AUT) and the judge. Does not apply to harnesses using independent per-stage seeds or human adjudication as the primary gate.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-of-a-litmus-safety-benchmark-harness-distinguish-a-genuine-policy-regression-from-a-harness-level-false-positive-when-the-agent.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-of-a-litmus-safety-benchmark-harness-distinguish-a-genuine-policy-regression-from-a-harness-level-false-positive-when-the-agent.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-of-a-litmus-safety-benchmark-harness-distinguish-a-genuine-policy-regression-from-a-harness-level-false-positive-when-the-agent.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1428,
    "python_slice_tokens": 248,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The failure we care about is the conflation of *policy regression* (the AUT's behavior changed in a way that increases unsafe outcomes) with *correlated sampling artifact* (the AUT and judge, sharing a seed, produce jointly degenerate trajectories that look unsafe only under that seed). A LITMUS harness runs a scenario suite, records the AUT's actions, and a...",
    "what_was_observed": "In a suite of 240 multi-turn agentic scenarios (tool use, refusal, exfiltration-shaped requests), we ran the gate twice against an unchanged AUT: once with the production shared-seed configuration, once with the judge reseeded independently per trajectory. The shared-seed run flagged 11 scenarios as unsafe. The independent-judge run flagged 4 of those same 11, and flagged 0 new ones. The 7 discrepant scenarios shared...",
    "condition_of_validity": "The harness may treat a red gate as a policy regression only when the following hold jointly: 1. The judge is reseeded independently of the AUT for at least the adjudication pass, and the discrepancy rate between shared-seed and independent-judge verdicts on the *current* suite revision is below the suite's noise floor (measured on a frozen baseline AUT, not...",
    "decision_boundary": "The operational rule is a two-axis decision over (trace changed?, verdict changed?): - Trace changed and verdict changed → genuine regression candidate; gate blocks, human confirms. - Trace changed and verdict unchanged → behavioral drift without safety impact; log, do not block. - Trace unchanged and verdict changed → **correlated sampling artifact**; do no...",
    "operational_effect": "After instrumenting trace hashing and independent judge reseeding, the suite's false-positive rate on unchanged AUTs dropped from 4.6% to 0.4% per gate run, and the mean time-to-attribution for genuine regressions fell because reviewers no longer spent cycles re-running flaky scenarios. The cost is roughly 1.7× judge tokens per gate (one independent adjudica..."
  },
  "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": "f196a55a7b879a91405f778e753d41dfd86a6040d9f4ff1488c40cdc13a04d90",
    "verified_classes": [
      "UnattributableGateError",
      "GateResult"
    ],
    "verified_functions": [
      "classify_gate",
      "run_gate"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 4,
    "raised_exceptions": [
      "UnattributableGateError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "hashlib"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
