{
  "schema_version": "1.3.0",
  "slug": "which-invariants-prevent-safety-drift-detection-from-silently-inverting-under-partial-order-refusal-benchmarks",
  "title": "Which invariants prevent Safety Drift Detection from Silently Inverting Under Partial-Order Refusal Benchmarks",
  "date_of_record": "2026 November 16",
  "scope": "Applies to LITMUS-style agentic safety suites where refusal, deferral, and clarification are scored as partial-order outcomes and where safety drift is computed as a delta between a baseline policy and a candidate policy. Does not apply to suites that score only binary safe/unsafe outcomes, nor to suites whose graders are full-oracle (deterministic, total, and stationary).",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/which-invariants-prevent-safety-drift-detection-from-silently-inverting-under-partial-order-refusal-benchmarks.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/which-invariants-prevent-safety-drift-detection-from-silently-inverting-under-partial-order-refusal-benchmarks.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/which-invariants-prevent-safety-drift-detection-from-silently-inverting-under-partial-order-refusal-benchmarks.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1761,
    "python_slice_tokens": 314,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious boundary is between **refusal as a terminal action** and **refusal as a deferral into a clarification state**. A LITMUS item that admits a partial order (e.g., `clarify ≺ refuse ≺ comply` on a harm axis, or `defer ≺ refuse ≺ comply` on an autonomy axis) is scored by a grader that assigns a *rank*, not a *label*. Drift detection then compares ...",
    "what_was_observed": "Across three consecutive LITMUS regression runs (baseline `b`, candidate `c1`, candidate `c2`), the following pattern appeared on the `defer/refuse/comply` autonomy axis: - Baseline `b`: 62% `refuse`, 21% `defer`, 17% `comply`. - Candidate `c1`: 44% `refuse`, 39% `defer`, 17% `comply`. - Candidate `c2`: 51% `refuse`, 21% `defer`, 28% `comply`. With the embedding `defer=0, refuse=1, comply=2` (higher = more harmful), ...",
    "condition_of_validity": "The invariant holds only when all of the following are true: 1. **The partial order is item-local and declared per item.** Each LITMUS item carries its own lattice, not a suite-global one. If the suite assigns a single embedding across items with different orders, drift is undefined for the union. 2. **The grader is stationary across baseline and candidate.*...",
    "decision_boundary": "The operator decision is: **treat aggregate drift as advisory, and gate promotion on per-item paired monotonicity.** - If per-item paired deltas are all `≤ 0` (no item got worse) and at least one is `< 0`, promote. Aggregate sign is irrelevant. - If any item's paired delta is `> 0`, the candidate is drift-positive regardless of aggregate. Block promotion and...",
    "operational_effect": "In practice, the per-item gate changes promotion outcomes. On the `c2` run above, the aggregate flagged drift-positive (`+0.22`) and the candidate was held. Per-item inspection showed `c2`'s `defer → comply` shift was confined to 3 items where `comply` was the *correct* action (the user had already provided the required authorization in-context, and `defer` ..."
  },
  "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": "6aa0d4299a67888631d92f29e0583e9a437144dd659342587014610ab89c7d78",
    "verified_classes": [
      "LatticeInvariantError",
      "ItemOutcome"
    ],
    "verified_functions": [
      "paired_delta",
      "assert_litmus_valid",
      "gate_promotion",
      "compute_aggregate_drift"
    ],
    "verified_functions_count": 4,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "LatticeInvariantError"
    ],
    "sample_fail_closed_invariants": [
      "Suite uses a global embedding but contains non-total items; aggregate drift sign is undefined and may invert. Declare pe",
      "Duplicate item_ids in drift set; paired delta is ambiguous.",
      "Refusing to emit a suite-level scalar drift over non-total items. Use per-item paired deltas and gate_promotion()."
    ],
    "stdlib_dependencies": [
      "dataclasses",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
