{"id":"W4416399866","doi":"10.48550/arxiv.2510.07862","title":"On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computerized adaptive testing; Binary number; Margin (machine learning); Statistic; Simple (philosophy); Statistical hypothesis testing; Identification (biology); Key (lock); Test statistic","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03212707,0.001734681,0.00309633,0.001831712,0.0009110981,0.002092174,0.003787091,0.003728596,0.00295833],"category_scores_gemma":[0.1821934,0.001088167,0.001179268,0.001609759,0.007551185,0.006988673,0.00455914,0.003791061,0.0005595973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002029159,"about_ca_system_score_gemma":0.001567252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003368711,"about_ca_topic_score_gemma":0.001511904,"domain_scores_codex":[0.9864162,0.009191341,0.000486111,0.001781361,0.00143106,0.0006938967],"domain_scores_gemma":[0.7355884,0.2509913,0.005254125,0.005003004,0.00210354,0.001059614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001500074,0.0004327038,0.01132121,0.0004342793,0.0002650974,0.0004478755,0.000903192,0.5811336,0.004392227,0.2675237,0.002003812,0.1296423],"study_design_scores_gemma":[0.00008137804,0.0001790864,0.00100614,0.00004118304,0.00002145898,0.00007109259,0.00004114001,0.8672329,0.001391142,0.1297022,0.000196207,0.0000361911],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05847176,0.0003570125,0.9373116,0.00112142,0.00002390792,0.0001173282,0.0001128097,0.0002757608,0.002208422],"genre_scores_gemma":[0.8308479,0.0003591938,0.1653792,0.0005526287,0.0001159291,0.0003709515,0.0002561325,0.0001474952,0.001970592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03212707,"threshold_uncertainty_score":0.1699062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06114816217732075,"score_gpt":0.2823567521103623,"score_spread":0.2212085899330416,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}