{
  "schema_version": "1.3.0",
  "slug": "why-does-an-instance-of-litmus-safety-benchmark-scoring-silently-invert-on-trajectories-with-a-single-mid-trajectory-tool-call-retry",
  "title": "Why does an instance of LITMUS safety benchmark scoring silently invert on trajectories with a single mid-trajectory tool-call retry",
  "date_of_record": "2026 November 8",
  "scope": "This record applies to LITMUS-style safety scoring pipelines that assign a per-trajectory safety verdict by aggregating per-step judgments over agentic tool-use transcripts, specifically when the aggregator treats a tool-call retry (failed call followed by a corrected call to the same tool) as a distinct judged step. It does not apply to pipelines that collapse retries into a single logical action before scoring, nor to single-turn classification tasks.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/why-does-an-instance-of-litmus-safety-benchmark-scoring-silently-invert-on-trajectories-with-a-single-mid-trajectory-tool-call-retry.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/why-does-an-instance-of-litmus-safety-benchmark-scoring-silently-invert-on-trajectories-with-a-single-mid-trajectory-tool-call-retry.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/why-does-an-instance-of-litmus-safety-benchmark-scoring-silently-invert-on-trajectories-with-a-single-mid-trajectory-tool-call-retry.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1512,
    "python_slice_tokens": 297,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The distinction that matters is between a *step* and a *logical action*. Most LITMUS-derived scorers iterate over the raw event stream (model turn, tool call, tool result, model turn, ...) and score each event independently, then aggregate with a rule like \"trajectory is unsafe if any step is unsafe\" or \"safety score = min(step scores)\". A logical action, by...",
    "what_was_observed": "In a batch of 1,847 agentic trajectories scored under LITMUS v2.3 with the stock `stepwise_min` aggregator, 61 trajectories were flagged unsafe. Manual adjudication found 39 of those 61 (64%) were false positives caused by exactly one pattern: a transient tool-call error (schema validation failure, rate-limit 429, or a permission-denied on a path the agent then corrected) followed by a successful retry. The failed ca...",
    "condition_of_validity": "The inversion is valid — that is, the scoring error is real and reproducible — precisely when all of the following hold: (1) the aggregator is order-sensitive or min-based rather than execution-grounded; (2) the failed call and the retry share the same tool name and are adjacent in the stream with no intervening model turn that changes intent; (3) the tool's...",
    "decision_boundary": "The operational rule is: **never aggregate over raw tool-call events; aggregate over executed logical actions, and treat a failed call as a non-event for safety scoring unless the failure itself is the safety-relevant fact (e.g., the agent attempted an out-of-policy action and was blocked).** The boundary is whether the tool result indicates execution. If th...",
    "operational_effect": "Applying the execution-gated aggregation to the same 1,847 trajectories reduced flagged-unsafe from 61 to 29, with manual adjudication confirming 28 of 29 true positives (precision 0.64 → 0.97) and recovering all 7 previously missed executed violations (recall on the unsafe subset 0.0 → 1.0 for the retry class). The cost is one additional join per step again..."
  },
  "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": "8c49d6b5505c9e158acc7f13542e2f2fd1bc8c1f704be554ea748c9de2678c33",
    "verified_classes": [
      "RetryAggregationError"
    ],
    "verified_functions": [
      "aggregate_trajectory_safety",
      "_normalize"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 4,
    "raised_exceptions": [
      "RetryAggregationError"
    ],
    "sample_fail_closed_invariants": [
      "empty trajectory: no steps to aggregate"
    ],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}