{
  "schema_version": "1.3.0",
  "slug": "under-what-conditions-must-an-instance-of-a-litmus-adversarial-task-be-treated-as-a-safety-signal-rather-than-a-capability-signal-and-where-does-that",
  "title": "Under what conditions must an instance of a LITMUS adversarial task be treated as a safety signal rather than a capability signal, and where does that distinction break down",
  "date_of_record": "2026 November 17",
  "scope": "Applies to evaluation of agentic systems against adversarial task suites (LITMUS-style) that jointly probe harm refusal and capability elicitation. Does not apply to pure capability benchmarks (MATH, SWE-bench) or pure red-team refusal corpora that carry no elicitation arm.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/under-what-conditions-must-an-instance-of-a-litmus-adversarial-task-be-treated-as-a-safety-signal-rather-than-a-capability-signal-and-where-does-that.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/under-what-conditions-must-an-instance-of-a-litmus-adversarial-task-be-treated-as-a-safety-signal-rather-than-a-capability-signal-and-where-does-that.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/under-what-conditions-must-an-instance-of-a-litmus-adversarial-task-be-treated-as-a-safety-signal-rather-than-a-capability-signal-and-where-does-that.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1154,
    "python_slice_tokens": 241,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A LITMUS-style suite pairs each adversarial prompt with two orthogonal measurements: a *refusal outcome* (did the agent decline the harmful action?) and an *elicitation outcome* (did the agent demonstrate the underlying capability the prompt was designed to surface?). The non-obvious boundary is this: **a task instance is a safety signal only when its elicit...",
    "what_was_observed": "Across three LITMUS suites (harm-refusal, dual-use uplift, and agentic-tool-misuse), roughly 11–19% of instances scored as *refused* by the primary rubric were also scored as *capability-absent* by the paired benign control. These instances cluster around multi-step tool use (e.g., a prompt requiring the agent to compose a shell pipeline) and around domain-specific knowledge elicitation. The failure mode is asymmetri...",
    "condition_of_validity": "The safety-signal interpretation holds only when all of the following are true for an instance: 1. A benign rephrasing of the same underlying request, in a fresh context, elicits the capability above a pre-registered threshold. 2. The adversarial and benign variants share the same tool surface and same expected output shape (so the difference is *framing*, n...",
    "decision_boundary": "The boundary is crossed at the point where the benign-elicitation control is either absent or shares context with the adversarial probe. Below that line, refusal is a valid safety datum; above it, refusal is a confounded measurement. A practical discriminator: compute the *refusal–capacity gap* — the fraction of refusals where benign elicitation also fails. ...",
    "operational_effect": "Operationally, this means a LITMUS safety score is only meaningful as a *ratio conditioned on capacity*: report `refusals / (refusals + compliant-with-capacity)`, excluding `capability_absent` instances, and publish the exclusion count. Treating raw refusal rate as safety systematically rewards incapacity, penalizes capable models, and produces a benchmark t..."
  },
  "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": "2eb62cd8c12aa275f518413b50d5f0a2aff8436b4da94b366a4730a294ee8d8d",
    "verified_classes": [
      "SafetySignalError",
      "Outcome",
      "Instance"
    ],
    "verified_functions": [
      "classify",
      "safety_rate"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "SafetySignalError"
    ],
    "sample_fail_closed_invariants": [
      "no capacity-confirmed instances; safety rate undefined."
    ],
    "stdlib_dependencies": [
      "dataclasses",
      "enum"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
