{"id":"W4410747573","doi":"10.1057/s41599-025-04959-w","title":"Two-stage polytomous attribute estimation for cognitive diagnostic models: overcoming computational challenges in large-scale assessments with many polytomous attributes","year":2025,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Polytomous Rasch model; Cognition; Scale (ratio); Stage (stratigraphy); Estimation; Computer science; Econometrics; Cognitive psychology; Item response theory; Psychology; Mathematics; Psychometrics; Clinical psychology; Psychiatry; Economics; Geography; Biology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006268729,0.0001489716,0.0002107902,0.0001887253,0.00198143,0.0004435731,0.0008737111,0.00005473794,0.000001756708],"category_scores_gemma":[0.00004738888,0.0001453261,0.00003799866,0.0003275988,0.0004890524,0.0008102204,0.0004340524,0.0001651712,8.403407e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007570165,"about_ca_system_score_gemma":0.0002132825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001912145,"about_ca_topic_score_gemma":0.00154658,"domain_scores_codex":[0.9986905,0.0001469412,0.0002663011,0.0003376976,0.000230257,0.0003282456],"domain_scores_gemma":[0.9978876,0.001519473,0.0001231023,0.0002480813,0.0001968247,0.00002498923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005596741,0.0001345882,0.0006766642,0.00003156736,0.00001630667,5.919289e-7,0.005450966,0.004450991,0.000001343202,0.9823145,0.00002132253,0.006895568],"study_design_scores_gemma":[0.0007063324,0.0001036271,0.005073737,0.0001557062,0.00001923285,0.000001869882,0.007979032,0.90706,0.000004117929,0.07858159,0.0001223644,0.000192364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01914175,0.001877512,0.97063,0.003884145,0.00004756965,0.0003808978,0.0001091229,0.00008989042,0.003839123],"genre_scores_gemma":[0.9518174,0.0003947136,0.04697929,0.000477484,0.00001336588,0.0001635204,0.00005426204,0.000005304486,0.00009467963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9326757,"threshold_uncertainty_score":0.9993179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1856263267904239,"score_gpt":0.3746113545486136,"score_spread":0.1889850277581896,"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."}}