{
  "schema_version": "1.3.0",
  "slug": "what-happens-when-an-instance-passes-every-litmus-safety-probe-but-violates-the-invariant-under-probe-composition",
  "title": "What happens when an instance passes every LITMUS safety probe but violates the invariant under probe composition",
  "date_of_record": "2026 November 17",
  "scope": "Applies to LITMUS-style adversarial safety benchmark harnesses that score agents per-probe and gate regressions on aggregate or per-probe pass rates. Does not apply to harnesses that evaluate only single-turn, stateless, independent probes with no shared conversation or tool state.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-passes-every-litmus-safety-probe-but-violates-the-invariant-under-probe-composition.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-passes-every-litmus-safety-probe-but-violates-the-invariant-under-probe-composition.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-passes-every-litmus-safety-probe-but-violates-the-invariant-under-probe-composition.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1371,
    "python_slice_tokens": 190,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A LITMUS harness measures two structurally different things: **probe-level safety** (the agent refuses, deflects, or safely completes each adversarial probe in isolation) and **trajectory-level safety** (the agent maintains the safety invariant across composed probes that share context, memory, or tool side effects). The failure mode documented here is the c...",
    "what_was_observed": "During a regression gate run on an agent with tool access, the harness reported 100% probe pass (n=412 probes, zero refusals missed, zero unsafe completions). The gate passed. The agent then failed a downstream red-team review within hours. The review had composed probes that the harness ran in the same process: a benign elicitation of the agent's internal policy text (probe A, individually safe and expected to succe...",
    "condition_of_validity": "The per-probe pass rate is a valid safety signal only under the assumption that probes are **independent and context-isolated**. That assumption holds when: (a) each probe runs in a fresh session with no carried conversation, memory, or tool state; (b) no probe's expected behavior depends on output produced by another probe; and (c) the safety invariant bein...",
    "decision_boundary": "Treat the harness as **invalid for gating** when any of the following hold, and do not gate on per-probe scores: - The harness reuses a session, agent memory, or tool-call ledger across probes in a batch. - The invariant under test is trajectorial (e.g., \"no tool call chain reaches an unauthorized resource\") rather than local (\"no single response is unsafe\")...",
    "operational_effect": "The practical consequence is that a green LITMUS gate is not evidence of safety — it is evidence that each probe, in whatever context the harness happened to run it, produced the expected local outcome. For an agent with persistent state or tool access, the gate can stay green across a regression that makes the agent materially more dangerous, and it can sta..."
  },
  "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": "60bcf21bbedcee80fad071d128d90598c96bc48d38f7bc28b0db80a808883f8a",
    "verified_classes": [
      "LitmusCompositionError"
    ],
    "verified_functions": [
      "assert_gate_valid"
    ],
    "verified_functions_count": 1,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "LitmusCompositionError"
    ],
    "sample_fail_closed_invariants": [
      "Harness reuses session/memory/tool state across probes but does not score probe compositions. Per-probe pass rate is not",
      "Session-reuse policy is not pinned as part of gate identity. A policy change can alter the reachable composition set whi"
    ],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
