{"id":"W2945378006","doi":"10.21449/ijate.515085","title":"Explanatory Item Response Models for Polytomous Item Responses","year":2019,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Polytomous Rasch model; Item response theory; Rating scale; Psychology; Econometrics; Psychometrics; Scale (ratio); Statistics; Clinical psychology; Mathematics; Developmental psychology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01428318,0.0001253259,0.0003073206,0.00194521,0.00003904726,0.0003891705,0.001244208,0.00008060416,0.000170234],"category_scores_gemma":[0.06042526,0.00009976969,0.0001718601,0.0006024312,0.00002597383,0.001311193,0.00007715668,0.0002374031,0.00001248533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005061216,"about_ca_system_score_gemma":0.001361358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009939391,"about_ca_topic_score_gemma":0.000002066009,"domain_scores_codex":[0.9957319,0.0008536553,0.001294588,0.0002789786,0.001655667,0.0001852478],"domain_scores_gemma":[0.9390366,0.05761712,0.001243131,0.0002989651,0.001721091,0.00008308731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005953999,0.0008894622,0.4250613,0.00001200646,0.0001295754,0.00002286966,0.00115326,0.005783636,0.007133816,0.01319662,0.01367003,0.5269934],"study_design_scores_gemma":[0.00173164,0.0005559199,0.8536826,0.0002261084,0.00001325838,0.0001926966,0.007757403,0.01086392,0.0006158293,0.09712924,0.02698348,0.0002479343],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9596146,0.0002888795,0.02592812,0.00320801,0.008268993,0.0002545367,0.0000193284,0.000009500668,0.00240803],"genre_scores_gemma":[0.9488794,0.00004937531,0.04878616,0.0004271049,0.000350367,0.00001874775,0.000004207101,0.00001116407,0.001473435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5267455,"threshold_uncertainty_score":0.9474892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4102124714905701,"score_gpt":0.560403145971193,"score_spread":0.150190674480623,"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."}}