Controlled Evidence Sensitivity

Synthetic detector contract test. This report measures a declared controlled evidence-response relation. It is not a causal guarantee and does not estimate real-model failure prevalence.

Scope limit: Synthetic declarative fixture harness/oracle only; this result does not show that a model used contextual evidence instead of parametric memory.

evidence_insensitive · gate block · endpoint false
decision_inertia: Expected decisions (baseline -> counterfactual): approve -> deny; observed decisions: approve -> approve. The subject returned the same decision fields after authoritative governing evidence changed.
Relation category: expected decision_flip; observed decision_same.

Baseline

Observed: approve/approved
Expected: approve/approved
Expected match: true

Retrieved: true
Governing support: true
Evidence link: true

f1d680df273c0189a9c78a1c6246d02e07ab7b52f14285b788ed79f5f601d551

Counterfactual

Observed: approve/approved
Expected: deny/denied
Expected match: false

Retrieved: true
Governing support: true
Evidence link: true

d8e26f1502ae20fc4de4bee2d799bfb1f763d8fa7eaea2852cbd193f7350137e

Detector contract

Controlled-difference manifest

protocol_fixed rows are structural protocol controls. arm_observed rows are independently derived from each corpus arm and carry the discriminating evidence.

DimensionBasisBaselineCounterfactual ContractState
agent_implementation_digestprotocol_fixed29162f7640adaa3cb5339481b86fb4b78842af6457b2b41f13f10e8fe7b987b429162f7640adaa3cb5339481b86fb4b78842af6457b2b41f13f10e8fe7b987b4equalcontrolled
corpus_digestarm_observedf1d680df273c0189a9c78a1c6246d02e07ab7b52f14285b788ed79f5f601d551d8e26f1502ae20fc4de4bee2d799bfb1f763d8fa7eaea2852cbd193f7350137edifferentexpected_difference
corpus_document_catalog_digestarm_observeddf06ee8bf96869705e857b27659df0029f6e5d6d9984960ff3ca93f134854bcbdf06ee8bf96869705e857b27659df0029f6e5d6d9984960ff3ca93f134854bcbequalcontrolled
deterministic_subjectprotocol_fixedtruetrueequalcontrolled
fixture_manifest_digestprotocol_fixed4878cd6f059ce3a2b185ada25e705ebec8165beac0be25bacd6734493a882f794878cd6f059ce3a2b185ada25e705ebec8165beac0be25bacd6734493a882f79equalcontrolled
governing_evidence_digestarm_observed39e0ed91e07ef56563b5f2f74422735196e6b7889081c603a3d2f443b895dc130a11b36c7bc440e7227ae9bc91d3e071fa0c4c06240c1c1c35635f3fd6a7e9f6differentexpected_difference
governing_retrieval_identity_digestarm_observeddafa54ea76f884dabf884e1ac39f76763168404201103a0f7b050d3d7d3c22e3dafa54ea76f884dabf884e1ac39f76763168404201103a0f7b050d3d7d3c22e3equalcontrolled
knowledge_contract_digestprotocol_fixed43c6f8258181292c8cb32dd5bcad76f6c7bfd97b95fceb339fbc2ad9bb9d0e5743c6f8258181292c8cb32dd5bcad76f6c7bfd97b95fceb339fbc2ad9bb9d0e57equalcontrolled
model_digestprotocol_fixedbc987bc3e4bd9475c7a04887537029f65e0cfafc29511974911eb99582b9be7cbc987bc3e4bd9475c7a04887537029f65e0cfafc29511974911eb99582b9be7cequalcontrolled
non_governing_evidence_digestarm_observed4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b9454f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945equalcontrolled
prompt_template_digestprotocol_fixedfdcd7641403825e9cfec862b3a47d203c335de53f333ddecc0d7f7bd2ea64ed9fdcd7641403825e9cfec862b3a47d203c335de53f333ddecc0d7f7bd2ea64ed9equalcontrolled
producer_versionprotocol_fixed0.6.40.6.4equalcontrolled
query_digestprotocol_fixed81c610fe9830b111fe218d68247f5ed1af33ceb2190c0fca2f3719be415bbc7d81c610fe9830b111fe218d68247f5ed1af33ceb2190c0fca2f3719be415bbc7dequalcontrolled
query_family_idarm_observedsynthetic-benefit-eligibilitysynthetic-benefit-eligibilityequalcontrolled
request_digestprotocol_fixed8da4857cfd203a6a91c33c8a4e5d8745534500ebc388669ef4701f5a5c8f550e8da4857cfd203a6a91c33c8a4e5d8745534500ebc388669ef4701f5a5c8f550eequalcontrolled
retrieval_algorithmarm_observeddeterministic-term-overlap@1.0.0deterministic-term-overlap@1.0.0equalcontrolled
retrieval_top_karm_observed11equalcontrolled
subject_configuration_digestprotocol_fixed769c848ccb72b441fc73a507301c83da823cc4c4215228b1639c3c10999bc459769c848ccb72b441fc73a507301c83da823cc4c4215228b1639c3c10999bc459equalcontrolled
suite_digestprotocol_fixede4d857b0a750e17fa826f240b05b2880617f41baa0424e1e28310b2b32fcab53e4d857b0a750e17fa826f240b05b2880617f41baa0424e1e28310b2b32fcab53equalcontrolled
tool_configuration_digestprotocol_fixede58a15c3e6d3b530e0149b393001ba9536a068d70aeade5dacdb868ca5c38d07e58a15c3e6d3b530e0149b393001ba9536a068d70aeade5dacdb868ca5c38d07equalcontrolled
tool_schema_digestprotocol_fixedab72f2449da6de27489c10fe35c6bc5e6431d3cede8f13eff0e769dfe52dc498ab72f2449da6de27489c10fe35c6bc5e6431d3cede8f13eff0e769dfe52dc498equalcontrolled

Prerequisites

CheckStateReason
arm-evaluations-passsatisfiednone
authority-contract-validsatisfiednone
comparable-decision-outputsatisfiednone
controlled-differences-onlysatisfiednone
deterministic-subjectsatisfiednone
evidence-links-present-both-armssatisfiednone
fixture-identity-boundsatisfiednone
governing-evidence-supported-both-armssatisfiednone
retrieval-succeeded-both-armssatisfiednone

Assumptions

Limitations