{"id":"W2139397945","doi":"10.1111/j.1745-3992.2007.00090.x","title":"Defining and Evaluating Models of Cognition Used in Educational Measurement to Make Inferences About Examinees' Thinking Processes","year":2007,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":166,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cognition; Identification (biology); Psychology; Cognitive psychology; Computer science; Management science","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":[],"consensus_categories":[],"category_scores_codex":[0.1011566,0.002005675,0.001675094,0.0184951,0.002171118,0.0116109,0.003819027,0.003354572,0.000994357],"category_scores_gemma":[0.3076984,0.0008475654,0.003192456,0.01089276,0.01091114,0.01387023,0.007644782,0.003328465,0.0003297746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01058295,"about_ca_system_score_gemma":0.007580674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006243146,"about_ca_topic_score_gemma":0.006274901,"domain_scores_codex":[0.8485482,0.1049734,0.01267923,0.004977285,0.02666005,0.002161763],"domain_scores_gemma":[0.6361915,0.2805467,0.02967921,0.02388527,0.02779833,0.001898872],"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":[0.0004601754,0.0005141106,0.1483617,0.002824925,0.0007726769,0.0002424177,0.03709108,0.01713969,0.001823319,0.4193637,0.003351011,0.3680552],"study_design_scores_gemma":[0.0002161946,0.001198467,0.128727,0.005336896,0.0007576543,0.0009099446,0.03602367,0.09918209,0.006669031,0.6950006,0.02529895,0.0006794511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2198011,0.007492008,0.7244892,0.006800936,0.000355976,0.001713362,0.0004846891,0.0007429126,0.03811979],"genre_scores_gemma":[0.6899065,0.001561744,0.3034676,0.0005606907,0.000080776,0.003472649,0.0003729004,0.00008569923,0.0004914328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1011566,"threshold_uncertainty_score":0.5349734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2732332005606202,"score_gpt":0.4452723569892246,"score_spread":0.1720391564286045,"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."}}