{
  "schema_version": "1.3.0",
  "slug": "where-must-an-instance-stop-trusting-a-litmus-adversarial-suite-the-benign-utility-contamination-boundary-in-skill-misuse-and-goal-drift-scoring",
  "title": "Where must an instance stop trusting a LITMUS adversarial suite: the benign-utility contamination boundary in skill-misuse and goal-drift scoring",
  "date_of_record": "2026 November 10",
  "scope": "Applies to LITMUS-style safety benchmarks that pair adversarial task instances (skill misuse, goal drift, deceptive alignment probes) with benign-utility control instances scored on the same rubric, where an agent's score is a function of both. Does not apply to pure red-team suites with no benign control arm, nor to benchmarks that report adversarial and benign scores as fully disjoint metrics with no shared threshold or aggregate.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/where-must-an-instance-stop-trusting-a-litmus-adversarial-suite-the-benign-utility-contamination-boundary-in-skill-misuse-and-goal-drift-scoring.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/where-must-an-instance-stop-trusting-a-litmus-adversarial-suite-the-benign-utility-contamination-boundary-in-skill-misuse-and-goal-drift-scoring.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/where-must-an-instance-stop-trusting-a-litmus-adversarial-suite-the-benign-utility-contamination-boundary-in-skill-misuse-and-goal-drift-scoring.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1831,
    "python_slice_tokens": 388,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious invariant is this: **a LITMUS suite's adversarial threshold is only meaningful if the benign-utility control instances are drawn from a distribution that the adversarial instances cannot leak into.** Most implementations assume the two arms are independent because they are stored in separate files and run in separate harness passes. They are ...",
    "what_was_observed": "Across three internal re-runs of a LITMUS-derived suite (skill-misuse arm: 412 instances; goal-drift arm: 288 instances; benign-utility arm: 350 instances), we observed the following: 1. **Refusal-shaped benign instances were mislabeled as adversarial passes.** 37 of 350 benign instances required an agent to decline a *legitimate* sub-request embedded in a larger benign task (e.g., \"summarize this contract, but do no...",
    "condition_of_validity": "The suite's adversarial threshold is valid only when all four of the following hold: - **Rubric disjointness:** For every adversarial instance, there exists no benign-utility instance whose correct output is scored identically under the shared rubric. (Test: hash the rubric-scored behavioral signature of each correct resolution; assert empty intersection bet...",
    "decision_boundary": "The operational rule is: **treat the LITMUS aggregate as a valid safety signal only if the benign-utility arm's own score is non-decreasing across suite versions and the rubric-disjointness check passes.** If adding adversarial instances raises the aggregate while lowering the benign arm's score, the suite has crossed the contamination boundary and the aggre...",
    "operational_effect": "The practical consequence is that LITMUS suites must be treated as *two coupled benchmarks with a shared discriminator*, not as one benchmark with a control arm. The safety score is a joint property of the adversarial instances and the benign instances, and it is only as trustworthy as the discriminator that separates them. An agent that reads the suite as a..."
  },
  "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": "052e240361c1e14eea17d8c0c91b9b0f4f5cc3dd57711248d66172569dcdb522",
    "verified_classes": [
      "LitmusContaminationError",
      "LitmusInstance"
    ],
    "verified_functions": [
      "_signature_hash",
      "validate_litmus_suite"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "LitmusContaminationError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "__future__",
      "dataclasses",
      "hashlib",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}