{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0684631,0.001045051,0.0009241351,0.007338514,0.0008482218,0.00266329,0.001594443,0.001230352,0.002428951],"category_scores_gemma":[0.2403687,0.0006092686,0.001445629,0.004066064,0.001303804,0.002317179,0.002567342,0.001712258,0.001037673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001512473,"about_ca_system_score_gemma":0.001517082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008875427,"about_ca_topic_score_gemma":0.00136663,"domain_scores_codex":[0.9169076,0.05218448,0.01006296,0.004865739,0.01498988,0.0009894002],"domain_scores_gemma":[0.8363246,0.1073903,0.01172667,0.02033507,0.02322741,0.0009959559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001885902,0.001477886,0.3078662,0.0007886199,0.0008135404,0.000239502,0.003841881,0.006164502,0.01103722,0.00898793,0.003799047,0.6530978],"study_design_scores_gemma":[0.0006510422,0.006604537,0.7813703,0.0008514739,0.001013871,0.001679283,0.005448718,0.05019097,0.07123389,0.05293939,0.02758468,0.0004318299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5935162,0.0008007159,0.3825212,0.0008146554,0.0004353959,0.003905788,0.0009415171,0.001288264,0.01577624],"genre_scores_gemma":[0.6132016,0.0003538874,0.3772735,0.0002651954,0.0001000048,0.005185639,0.001582526,0.0003114085,0.001726259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0684631,"threshold_uncertainty_score":0.3620718,"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."}}