{"id":"W2026285281","doi":"10.1177/0013164412448652","title":"Linking Cut-Scores Given Changes in the Decision-Making Process, Administration Time, and Proportions of Item Types Between Successive Administrations of a Test for a Large-Scale Assessment Program","year":2012,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Process (computing); Scale (ratio); Psychology; Equating; Test score; Psychometrics; Computer science; Applied psychology; Statistics; Standardized test; Clinical psychology; Mathematics education; 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":[0.005657167,0.0001133874,0.0002512579,0.0001834839,0.0001789313,0.00007223349,0.0002534943,0.00007389515,0.0001353066],"category_scores_gemma":[0.02515524,0.00006552611,0.00004455192,0.0007345604,0.0001090168,0.0001243206,0.0000295709,0.0001131982,7.821893e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001673814,"about_ca_system_score_gemma":0.0001249706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000121321,"about_ca_topic_score_gemma":0.00003806011,"domain_scores_codex":[0.9977934,0.0002081485,0.0006247197,0.0003009626,0.0008647307,0.0002080651],"domain_scores_gemma":[0.9791998,0.01950273,0.0005142263,0.0001785856,0.0005393837,0.00006524011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004100846,0.001891777,0.834395,0.00004127644,0.00001571342,1.448455e-7,0.0009566533,0.00000241003,0.0001277041,0.001128971,0.0004911184,0.1609082],"study_design_scores_gemma":[0.0001959511,0.0008120564,0.9624704,0.0001590455,0.00002463277,0.000006001675,0.0009741313,0.000127099,0.00006104328,0.03438451,0.0007006237,0.00008458436],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984461,0.0006503994,0.006269514,0.005139441,0.0001923584,0.001492959,0.0002815747,0.0000148493,0.00149791],"genre_scores_gemma":[0.9531385,0.00001002809,0.04621157,0.00004997371,0.0001691006,0.0003761067,0.00002869573,0.000003609639,0.00001235743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1608236,"threshold_uncertainty_score":0.9830563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4302050027001809,"score_gpt":0.5329682362061104,"score_spread":0.1027632335059295,"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."}}