{"id":"W2135663628","doi":"10.1177/0265532208097336","title":"Cognitive diagnostic assessment of L2 reading comprehension ability: Validity arguments for Fusion Model application to <i>LanguEdge</i> assessment","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":175,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reading comprehension; Psychology; Cognition; Test (biology); Profiling (computer programming); Dependability; Comprehension; Reading (process); Cognitive psychology; Computer science; Linguistics","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":[0.005607481,0.000233323,0.000566214,0.0003597184,0.0004046212,0.00006082846,0.000509802,0.00009164836,0.00002018725],"category_scores_gemma":[0.1339034,0.0001909338,0.0001271029,0.001691146,0.00007605331,0.0001761379,0.0003434014,0.0001987398,0.000007722714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000126566,"about_ca_system_score_gemma":0.0001264369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00012942,"about_ca_topic_score_gemma":0.000006228173,"domain_scores_codex":[0.9961553,0.0004159203,0.001004955,0.0008236492,0.001181548,0.0004186427],"domain_scores_gemma":[0.9124872,0.0851215,0.000710158,0.0006375588,0.0008672672,0.0001762872],"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":[0.00003764888,0.0003782486,0.6663653,0.00008788145,0.00002349876,0.0000170198,0.002140289,0.01127237,0.1008787,0.00018096,0.0006185359,0.2179995],"study_design_scores_gemma":[0.0009548515,0.0003929524,0.4863092,0.000242554,0.00005246457,0.00002515564,0.002254783,0.501873,0.003340098,0.00416316,0.00004141528,0.0003504124],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5328215,0.00002596287,0.4643598,0.00004385342,0.0001190898,0.0007316874,0.00004269867,0.00007494368,0.001780404],"genre_scores_gemma":[0.6565592,0.000003071366,0.342977,0.0001693233,0.0000724407,0.0001264413,0.0000228743,0.00001553337,0.00005407738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4906006,"threshold_uncertainty_score":0.873392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4824119830634888,"score_gpt":0.5159648486704076,"score_spread":0.03355286560691884,"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."}}