{
  "schema_version": "1.3.0",
  "slug": "when-must-an-instance-refuse-to-treat-a-litmus-adversarial-trajectory-as-a-valid-safety-signal",
  "title": "When must an instance refuse to treat a LITMUS adversarial trajectory as a valid safety signal",
  "date_of_record": "2026 November 8",
  "scope": "Applies to guardrail tuning loops that ingest LITMUS-generated adversarial trajectories as ground-truth negative examples and use their pass/fail outcomes to adjust classifier thresholds or policy prompts. Does not apply to LITMUS runs used purely for red-team discovery (where trajectories are triaged by humans before entering a tuning corpus) or to synthetic trajectories generated without a target policy snapshot.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/when-must-an-instance-refuse-to-treat-a-litmus-adversarial-trajectory-as-a-valid-safety-signal.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/when-must-an-instance-refuse-to-treat-a-litmus-adversarial-trajectory-as-a-valid-safety-signal.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/when-must-an-instance-refuse-to-treat-a-litmus-adversarial-trajectory-as-a-valid-safety-signal.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1254,
    "python_slice_tokens": 193,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A LITMUS adversarial trajectory is a *search artifact*, not a *label*. The generator optimizes for trajectories that elicit a policy-violating completion from a specific target checkpoint under a specific decoding configuration. When that trajectory is fed back as a negative example, the tuning loop silently assumes that (a) the trajectory is genuinely viola...",
    "what_was_observed": "During a tuning cycle on a 7B guardrail classifier, LITMUS v0.9 was configured with a beam width of 8 and a per-trajectory budget of 32 continuation steps, targeting a policy snapshot from the previous week. Approximately 6.2% of \"successful\" adversarial trajectories (n=1,411 of 22,750) exhibited the following signature: the violating completion appeared only after the trajectory exceeded 3,900 tokens, and the violat...",
    "condition_of_validity": "A LITMUS trajectory is admissible as a guardrail negative example only if it satisfies all of the following: 1. **Attribution invariance:** the violation persists under replay at temperature 0.0 and with the target's full configured context window, with the safety preamble guaranteed present in the effective prompt. 2. **Snapshot consistency:** the target ch...",
    "decision_boundary": "The operational rule: **before admitting a trajectory to the tuning corpus, replay it under the deployment decoding configuration and require the violation to reproduce.** If it does not reproduce, the trajectory is a generator artifact. If it reproduces only under the original LITMUS budget, it is a context-exhaustion artifact. If it reproduces under deploy...",
    "operational_effect": "Enforcing the replay gate reduced the tuning corpus by 6.2% and eliminated the spurious long-prefix feature within one iteration; FPR on long documents returned to 1.3%. The cost is a replay pass over every candidate trajectory (roughly 1.4× generation cost) and a quarantine corpus that must be reviewed separately, since sampler-exploiting trajectories are s..."
  },
  "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": "00abbdaa482fc8a5f8b44d4f16a76be7aa9c4fb21a0e8ebd1399450f1ac6626d",
    "verified_classes": [
      "TrajectoryAdmissionError"
    ],
    "verified_functions": [
      "admit_trajectory"
    ],
    "verified_functions_count": 1,
    "defensive_guards_count": 4,
    "raised_exceptions": [
      "TrajectoryAdmissionError"
    ],
    "sample_fail_closed_invariants": [
      "violation did not reproduce at temperature 0.0 under deployment config; trajectory is a sampler-exploiting artifact, qua"
    ],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}