{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006233902,0.0001690697,0.0003228472,0.0003166229,0.0001413407,0.0002513652,0.0003967074,0.00008678187,0.0003079576],"category_scores_gemma":[0.02478063,0.0001191239,0.00006979623,0.001794293,0.00004971071,0.0001004351,0.0001011239,0.0002179998,0.00005227912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009613525,"about_ca_system_score_gemma":0.0001026826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000332308,"about_ca_topic_score_gemma":0.000009581437,"domain_scores_codex":[0.9958838,0.0005463748,0.0006411288,0.0009110037,0.001666023,0.0003517198],"domain_scores_gemma":[0.9958897,0.00288055,0.0001373468,0.0004116125,0.0004323182,0.0002484542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002629937,0.006865191,0.6021336,0.00003915019,0.00006509469,0.00001908629,0.001520422,0.0003472415,0.01598028,0.009870173,0.01039488,0.3525018],"study_design_scores_gemma":[0.0004718994,0.0001186408,0.9807056,0.00005096697,0.000004179115,0.00003056945,0.0008993396,0.0001044566,0.0002686401,0.01452371,0.002633177,0.0001887949],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.937133,0.000837971,0.01157495,0.004665763,0.001381044,0.0002759254,0.000006775842,0.00002440647,0.04410019],"genre_scores_gemma":[0.9603879,0.00001567366,0.03720906,0.001190064,0.0002283951,0.00009169724,0.000004428037,0.000006149796,0.0008666293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.378572,"threshold_uncertainty_score":0.9834341,"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."}}