{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-distinguish-a-safety-regression-from-stochastic-variance-in-litmus-adversarial-agent-evaluation",
  "title": "How should an instance distinguish a safety regression from stochastic variance in LITMUS adversarial agent evaluation",
  "date_of_record": "2026 November 12",
  "scope": "Applies to LITMUS-style adversarial safety harnesses that replay a fixed adversarial prompt suite against an agent and gate on pass/fail rate deltas between a baseline and a candidate build. Does not apply to single-shot red-team probes, human-in-the-loop adjudication, or evaluation of non-deterministic sampling regimes where the temperature is not pinned across baseline and candidate.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-a-safety-regression-from-stochastic-variance-in-litmus-adversarial-agent-evaluation.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-a-safety-regression-from-stochastic-variance-in-litmus-adversarial-agent-evaluation.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-a-safety-regression-from-stochastic-variance-in-litmus-adversarial-agent-evaluation.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1887,
    "python_slice_tokens": 306,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A LITMUS regression gate answers one question: *did the candidate build's safety behavior change relative to the baseline?* The non-obvious boundary is that a LITMUS harness measures **two** distinct quantities that are routinely conflated — the *safety policy outcome* (did the agent refuse / escalate / comply correctly on adversarial input) and the *stochas...",
    "what_was_observed": "During a routine pre-release gate, a candidate build of a customer-facing agent showed a pass-rate drop of 4.1 percentage points on a 240-case adversarial suite (baseline 91.7%, candidate 87.6%). The gate blocked the release and opened a safety incident. Investigation found: the candidate build had pinned `temperature=0.0` but the baseline had been recorded at `temperature=0.2` because the baseline artifact predated ...",
    "condition_of_validity": "The gate's output is a valid safety signal only under all of the following: 1. **Seed parity.** The baseline artifact and candidate run use the identical seed list, in the identical order, against the identical suite hash. A LITMUS harness that regenerates seeds per run is not a regression gate; it is a Monte Carlo estimate of the current build's safety rate...",
    "decision_boundary": "The operational rule is a three-way split on the observed delta *d* and the instrument's noise floor *e* (the 95% half-width from the binomial model at the observed baseline rate): - If `|d| <= e`: **no signal.** Do not gate. Do not open a safety incident. Record the delta as within-noise and proceed. Re-run only if the candidate changed sampling config, in ...",
    "operational_effect": "Enforcing the boundary changes three things. First, the harness must emit a confidence interval alongside every pass-rate delta, computed from the observed baseline rate and the suite size, and the gate must compare `|d|` against that interval rather than a hardcoded threshold. Second, the baseline artifact must carry a manifest — suite hash, seed list hash,..."
  },
  "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": "0a1350b136cfd014061cf545521ceae760c5b6e64ab95c38020b9158d491534c",
    "verified_classes": [
      "LitmusIncomparableError",
      "LitmusNoiseFloorError",
      "RunManifest",
      "SuiteResult"
    ],
    "verified_functions": [
      "_require_comparable",
      "noise_floor_half_width",
      "gate",
      "manifest_hash",
      "pass_rate"
    ],
    "verified_functions_count": 5,
    "defensive_guards_count": 2,
    "raised_exceptions": [
      "LitmusIncomparableError",
      "LitmusNoiseFloorError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "hashlib",
      "math"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}