{"id":"W2042334535","doi":"10.1037/a0014269","title":"A proposed framework for conducting data-based test analysis.","year":2008,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Extant taxon; Computer science; Test theory; Test data; Data mining; Psychometrics; Statistics; Mathematics; Software engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"category_scores_codex":[0.03781359,0.0003193908,0.001172152,0.0009375089,0.0005751526,0.0001846911,0.003426444,0.0003788302,0.0008598824],"category_scores_gemma":[0.6951944,0.0001968979,0.0004851947,0.01005608,0.0004395001,0.0002186878,0.0003542438,0.0005752073,0.00004839182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002496551,"about_ca_system_score_gemma":0.00004560177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007286564,"about_ca_topic_score_gemma":6.142022e-7,"domain_scores_codex":[0.9914123,0.003347993,0.001419141,0.002070588,0.001034681,0.0007153212],"domain_scores_gemma":[0.6658209,0.328798,0.0009137862,0.003605639,0.0005429289,0.0003187463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001820923,0.000807958,0.1924505,0.000009683715,0.0002281868,0.00003510245,0.000131495,0.0003097192,0.001542757,0.002469177,0.006091946,0.7957414],"study_design_scores_gemma":[0.001817757,0.001400934,0.3585839,0.00002535263,0.0005112675,0.00006721015,0.0005433851,0.06759359,0.001766987,0.5195189,0.04707084,0.001099904],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03866244,0.0003705765,0.9553593,0.001329856,0.001049882,0.0005131687,0.00006577071,0.0002361931,0.00241282],"genre_scores_gemma":[0.1863574,0.00001096867,0.811788,0.001327331,0.0002629391,0.00003952916,0.00001914619,0.00001593691,0.0001788495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7946415,"threshold_uncertainty_score":0.9907734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9565826883810709,"score_gpt":0.7111345330937316,"score_spread":0.2454481552873392,"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."}}