{"id":"W4409449514","doi":"10.31219/osf.io/tjxab_v2","title":"Fitting item response theory models using deep learning computational frameworks","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Connaught Fund","keywords":"Item response theory; Computer science; Deep learning; Artificial intelligence; Econometrics; Machine learning; Mathematics; Statistics; Psychometrics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001896474,0.000270011,0.0003772865,0.0006574061,0.000386012,0.0002928078,0.001890115,0.001184519,0.00004341415],"category_scores_gemma":[0.0008170155,0.000271378,0.0002026646,0.0006025918,0.00009230468,0.0003527679,0.004725374,0.002853182,0.0000106791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001044938,"about_ca_system_score_gemma":0.0002810965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002850714,"about_ca_topic_score_gemma":0.000003711031,"domain_scores_codex":[0.9973478,0.0007351896,0.0004295676,0.000890288,0.0002865988,0.0003106077],"domain_scores_gemma":[0.996029,0.002466735,0.0002625498,0.001008698,0.0001777128,0.00005528648],"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":[0.00002584425,0.00001468074,0.0001371088,0.00001640685,0.00009675891,0.00001185751,0.0003064797,0.7384234,0.000003751866,0.2417948,0.00002741305,0.01914151],"study_design_scores_gemma":[0.00005075118,0.000005607926,0.00007783574,0.00009569576,0.00003096569,0.000004768392,0.0000713086,0.6383508,0.00001561785,0.3610834,0.00004415102,0.0001690717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008090754,0.000387382,0.988564,0.0007399251,0.000240054,0.0001092237,0.000008374441,0.0008689715,0.0009913768],"genre_scores_gemma":[0.428739,0.00001052766,0.5700476,0.00050995,0.00002642405,0.000009368681,0.00003424056,0.000007358065,0.0006154842],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4206483,"threshold_uncertainty_score":0.9999738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0222703727686225,"score_gpt":0.2917846797853701,"score_spread":0.2695143070167476,"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."}}