{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2714573,0.003200294,0.002080447,0.003142649,0.001665593,0.003276737,0.004212411,0.002650799,0.00177714],"category_scores_gemma":[0.509171,0.001539727,0.007291072,0.002867122,0.002644445,0.004136882,0.004024792,0.005144953,0.0009012755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00150554,"about_ca_system_score_gemma":0.002259051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006178995,"about_ca_topic_score_gemma":0.002579806,"domain_scores_codex":[0.6455677,0.3309653,0.00627168,0.008222916,0.006681892,0.002290514],"domain_scores_gemma":[0.2530895,0.6753953,0.0179403,0.04292398,0.009905215,0.0007458191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008888516,0.004636406,0.8214782,0.000530131,0.009849063,0.0006519504,0.01727443,0.03145948,0.003477057,0.01145927,0.001186592,0.08910883],"study_design_scores_gemma":[0.001260125,0.01187693,0.2347156,0.0003898796,0.004397534,0.0006626392,0.004456601,0.7072185,0.0147333,0.01621316,0.003569694,0.0005060689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7623218,0.0002086574,0.2340697,0.0002669001,0.00008460274,0.00146475,0.0002601174,0.0003392673,0.0009841397],"genre_scores_gemma":[0.9215006,0.00006217453,0.07502872,0.0001516894,0.00004614087,0.001918442,0.0004001315,0.0001998546,0.0006922315],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2714573,"threshold_uncertainty_score":0.8984229,"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."}}