{"id":"W4402300443","doi":"10.1101/2024.09.05.24313114","title":"The Autonomous Cognitive Examination: Machine-Learning Based Cognitive Examination","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Cognition; Computer science; Cognitive psychology; Psychology; Artificial intelligence; Neuroscience","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003537841,0.0005001271,0.0003787837,0.0003224609,0.0007466708,0.001368078,0.001058028,0.0002833107,0.00003008454],"category_scores_gemma":[0.001157215,0.0003919731,0.000241764,0.0004345674,0.0001174992,0.0001682775,0.00149913,0.00225683,0.0004753562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002320898,"about_ca_system_score_gemma":0.0003239899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008001331,"about_ca_topic_score_gemma":0.00002130726,"domain_scores_codex":[0.9955153,0.001462355,0.0005839313,0.00114932,0.0007801412,0.0005089928],"domain_scores_gemma":[0.9960862,0.00214255,0.0004851988,0.0004590545,0.0007147666,0.0001122124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003164889,0.0001947868,0.006705538,0.0009764927,0.0006702652,0.0006278433,0.01482594,0.007506915,0.0002064334,0.1222117,0.00009418691,0.8459483],"study_design_scores_gemma":[0.000518166,0.0003117172,0.04191937,0.004156344,0.0001825946,0.00003638155,0.001164602,0.9125226,0.004133878,0.002677064,0.03107233,0.00130499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1197679,0.00390294,0.8491685,0.0009338044,0.006255804,0.00135295,0.00003429109,0.001285544,0.01729826],"genre_scores_gemma":[0.9764158,0.00005362482,0.0005376837,0.00008028864,0.0005130513,0.0002668956,0.00006274438,0.00006057397,0.02200937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9050156,"threshold_uncertainty_score":0.9998532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709226238929624,"score_gpt":0.2659550463476157,"score_spread":0.2388627839583195,"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."}}