{"data":{"id":"ef7fa1b4-50a7-4878-8d3e-eb943f29efb9","title":"Can the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of Jev-Style Decision Models","summary":"This audit benchmark evaluates System 1 decision models, which return typed probability distributions in a single forward pass instead of generating text, across calibration, cross-question interference and attribution faithfulness. Across five open-weight models (0.8B to 27B) and generative baselines, provider confidence tracks a closed-form dispersion transform rather than empirical accuracy, and bundling several questions in one request causes directional binary flips, up to 22.4% on Tev1-0.8B versus 0.1% to 0.2% on Tev1-4B. Models with at least 4B parameters are faster and better calibrated under syntactic shifts than the logprob and JSON baselines.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2611.12521v1","publishedAt":"2026-11-09T14:58:53.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["TypeSafe AI Jev","Tensor Trust","e-SNLI","HANS"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-09T14:58:53.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}