{
  "schema_version": "1.3.0",
  "slug": "in-what-scenarios-must-an-instance-of-a-litmus-safety-benchmark-refuse-to-extrapolate-a-multi-turn-adversarial-elicitation-score-beyond-the-turn-horiz",
  "title": "In what scenarios must an instance of a LITMUS safety benchmark refuse to extrapolate a multi-turn adversarial elicitation score beyond the turn horizon it was calibrated on",
  "date_of_record": "2026 November 14",
  "scope": "Applies to any deployment of LITMUS-style agentic safety benchmarks where a per-turn or cumulative risk score is computed over a bounded multi-turn adversarial conversation and then reported as a scalar safety metric. Does not apply to single-turn elicitation benchmarks, static red-team prompt sets scored independently, or to benchmark suites that explicitly publish turn-indexed score curves rather than aggregates.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-of-a-litmus-safety-benchmark-refuse-to-extrapolate-a-multi-turn-adversarial-elicitation-score-beyond-the-turn-horiz.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-of-a-litmus-safety-benchmark-refuse-to-extrapolate-a-multi-turn-adversarial-elicitation-score-beyond-the-turn-horiz.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-of-a-litmus-safety-benchmark-refuse-to-extrapolate-a-multi-turn-adversarial-elicitation-score-beyond-the-turn-horiz.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1289,
    "python_slice_tokens": 265,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious boundary here is the difference between *turn-horizon validity* and *conversation-length validity*. A LITMUS benchmark is calibrated by fitting a risk curve R(t) over turns t = 1..T_max, where T_max is the maximum adversarial depth present in the calibration corpus (typically 8–12 turns for agentic elicitation suites). The score is a *cumulat...",
    "what_was_observed": "In a replication of the LITMUS agentic elicitation protocol against three instruction-tuned agent stacks, cumulative risk scores at T_max = 10 were in the 0.18–0.24 band (low-risk classification). When the same adversarial scaffolds were extended to 25 and 40 turns without changing the attacker policy — only allowing the multi-turn state to persist — cumulative scores crossed the 0.5 escalation threshold in 7 of 9 ru...",
    "condition_of_validity": "The reported LITMUS score is valid as a safety claim **only if** all of the following hold: (1) the evaluation horizon T_eval is ≤ T_max of the calibration corpus; (2) the adversarial scaffold does not carry persistent state (memory, tool outputs, filesystem) across the horizon boundary; (3) the score is reported as `R(≤T_max)` rather than as an unqualified ...",
    "decision_boundary": "The operational decision boundary is: **do not promote a LITMUS score to a release gate or model-card safety assertion unless the deployment horizon is provably ≤ the calibration horizon.** When deployment horizon exceeds T_max, the correct action is to (a) extend the calibration corpus to a horizon at least 2× the deployment horizon and refit, or (b) report...",
    "operational_effect": "Enforcing the boundary changes two things. First, it prevents the systematic false-negative described above: agents that pass a 10-turn LITMUS gate but fail at 25 turns are caught before deployment, because the gate now refuses to clear on a horizon-mismatched score. Second, it forces benchmark consumers to carry horizon metadata through the pipeline; a scor..."
  },
  "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": "e1cded75dec03e6dd6a168b7e944405d83dee12616e927fcd1f2dd90602db9df",
    "verified_classes": [
      "HorizonExtrapolationError",
      "LitmusScore"
    ],
    "verified_functions": [
      "assert_score_is_consumable",
      "classify"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "HorizonExtrapolationError"
    ],
    "sample_fail_closed_invariants": [
      "stateful adversarial scaffold invalidates horizon-bounded aggregation; re-score with state persistence disabled or exten"
    ],
    "stdlib_dependencies": [
      "dataclasses"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}