{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1170323,0.002331492,0.001666188,0.01088661,0.003320565,0.01568022,0.008019691,0.005008065,0.005264871],"category_scores_gemma":[0.1556108,0.001362383,0.002818655,0.008583164,0.01193054,0.008933496,0.008489103,0.005636294,0.003381875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006352454,"about_ca_system_score_gemma":0.02269909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007055275,"about_ca_topic_score_gemma":0.005270126,"domain_scores_codex":[0.8820273,0.08053266,0.008631811,0.008064193,0.0192751,0.001468851],"domain_scores_gemma":[0.8628222,0.0804963,0.007369411,0.01804485,0.02697308,0.004294208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000532279,0.0001888097,0.003330164,0.0007744307,0.0001542288,0.0002642296,0.002790856,0.005586376,0.0007296776,0.8302676,0.008872573,0.1469877],"study_design_scores_gemma":[0.0001330352,0.0001913521,0.001730812,0.001299398,0.00009435198,0.0005579435,0.001622639,0.05086049,0.001055572,0.8654759,0.07687627,0.0001022204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007677265,0.0003375605,0.987468,0.003764984,0.00009905321,0.001833496,0.0002646689,0.0003734427,0.0050911],"genre_scores_gemma":[0.01083333,0.0001206921,0.9856033,0.0003725494,0.00003589253,0.002356951,0.000257442,0.00002750784,0.0003922214],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1170323,"threshold_uncertainty_score":0.6189333,"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."}}