{"id":"W2955358615","doi":"10.1177/0734282919861269","title":"Linking Test-Taking Process to Performance Through Mixed-Effects Regression Models: A Response Process–Based Validation Study","year":2019,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Test (biology); Process (computing); Logistic regression; Sample (material); Comprehension; Outcome (game theory); Active listening; Statistics; Machine learning; Computer science; 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":[0.01576492,0.0002744548,0.0005572762,0.001130351,0.0002738485,0.0003730475,0.001202941,0.00008803803,0.000145127],"category_scores_gemma":[0.02338597,0.0001849622,0.0001558533,0.003124122,0.00002563083,0.00135306,0.00006482781,0.0004964643,0.00002765205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003024103,"about_ca_system_score_gemma":0.001226922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002265987,"about_ca_topic_score_gemma":4.720328e-7,"domain_scores_codex":[0.9927058,0.001072755,0.00159612,0.0006137198,0.003659658,0.0003519595],"domain_scores_gemma":[0.9722893,0.02173495,0.002818595,0.0005829648,0.002385316,0.000188907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000935072,0.002479262,0.8438839,0.0001082836,0.00004958252,0.000006683594,0.004454777,0.1033142,0.001539088,0.00009624954,0.000876296,0.04225662],"study_design_scores_gemma":[0.001671849,0.002862329,0.9503776,0.001019513,0.0000406047,0.00005131283,0.008187062,0.01467826,0.001178696,0.01914258,0.0004649218,0.0003252687],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499188,0.00008336778,0.04292556,0.002045335,0.00262123,0.0008496195,0.00000240965,0.00002263775,0.001531036],"genre_scores_gemma":[0.9268071,0.000005820346,0.07221579,0.0004065545,0.0003115965,0.00006326043,0.000001906599,0.00002202796,0.0001659397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1064937,"threshold_uncertainty_score":0.9848405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3323818155501208,"score_gpt":0.5538929842036837,"score_spread":0.2215111686535629,"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."}}