{"id":"W3131054533","doi":"10.1177/0013164421991211","title":"A Polytomous Scoring Approach to Handle Not-Reached Items in Low-Stakes Assessments","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Polytomous Rasch model; Test (biology); Psychology; Item response theory; Statistics; Psychometrics; Clinical psychology; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01477829,0.00168057,0.001554989,0.004733684,0.001258042,0.001666961,0.002823241,0.001079486,0.006284274],"category_scores_gemma":[0.0714834,0.0006352294,0.001154533,0.004629186,0.001859331,0.002457872,0.003156094,0.002043651,0.001433049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009391127,"about_ca_system_score_gemma":0.002960726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005511226,"about_ca_topic_score_gemma":0.009199074,"domain_scores_codex":[0.9754165,0.01196833,0.002405975,0.003551614,0.006083833,0.0005738548],"domain_scores_gemma":[0.9436491,0.02616739,0.007738001,0.008535692,0.01299348,0.0009164298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006353249,0.0006732463,0.05511461,0.0004717818,0.0003356997,0.0003515909,0.001508768,0.02747511,0.009001994,0.01222333,0.005851143,0.8863573],"study_design_scores_gemma":[0.000449437,0.002207514,0.0919975,0.0003468897,0.0003676385,0.002185423,0.001525082,0.8341638,0.01123809,0.03925587,0.01570041,0.0005621695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07969949,0.0001286925,0.9143369,0.0002166708,0.0001060377,0.001988378,0.0002048905,0.00104485,0.002274051],"genre_scores_gemma":[0.2244228,0.00009562118,0.7717571,0.0001085153,0.00004688502,0.001431692,0.000336902,0.0001470233,0.001653472],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01477829,"threshold_uncertainty_score":0.07815599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8074745264456583,"score_gpt":0.5362121694680764,"score_spread":0.2712623569775819,"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."}}