{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000845172,0.000189661,0.000229308,0.0002096889,0.0001005622,0.00008105049,0.0007411875,0.00009335561,0.00000446693],"category_scores_gemma":[0.001008467,0.0001291558,0.0000452839,0.0004546646,0.00005998148,0.000280051,0.0006088802,0.0008868808,0.00000674566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000054984,"about_ca_system_score_gemma":0.0002713609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004303211,"about_ca_topic_score_gemma":0.000008405509,"domain_scores_codex":[0.998656,0.0002840176,0.0003304617,0.0002879026,0.0002581455,0.0001834496],"domain_scores_gemma":[0.9974062,0.001493266,0.0003341714,0.0005875312,0.0001531745,0.00002563871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001912494,0.00009902012,0.06951305,0.0001560396,0.0000466117,0.00001541764,0.003849954,0.8989037,0.00001968834,0.003059322,0.0000718308,0.02407408],"study_design_scores_gemma":[0.0001943919,0.0002155803,0.2854291,0.001143041,0.000009093886,0.000002608881,0.0001098591,0.7120406,0.00006094067,0.0006077325,0.00001225757,0.0001747731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7938647,0.00002125893,0.2035898,0.0007428775,0.0001498771,0.0002671455,0.000008299734,0.00008398342,0.001272015],"genre_scores_gemma":[0.9858699,8.633643e-7,0.01375387,0.0001981282,0.00002677879,0.00003509911,0.000004223277,0.000004728014,0.0001063584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2159161,"threshold_uncertainty_score":0.526682,"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."}}