{"id":"W3197086727","doi":"10.3390/educsci11090472","title":"Analyzing Cognitive Demands of a Scientific Reasoning Test Using the Linear Logistic Test Model (LLTM)","year":2021,"lang":"en","type":"article","venue":"Education Sciences","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Test (biology); Construct (python library); Cognition; Computer science; Variance (accounting); Psychology; Multiple choice; Science education; Mathematics education; Scientific reasoning; Item response theory; Logistic regression; Cognitive psychology; Artificial intelligence; Natural language processing; Machine learning; Psychometrics; Mathematics; Developmental psychology; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02058629,0.001216808,0.001017041,0.002348837,0.000547597,0.002845378,0.001555155,0.0009763165,0.003828279],"category_scores_gemma":[0.1305787,0.0005918671,0.00237559,0.002427489,0.001116004,0.002300616,0.002175116,0.001910573,0.0006325829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001543748,"about_ca_system_score_gemma":0.002040485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004875022,"about_ca_topic_score_gemma":0.004944345,"domain_scores_codex":[0.9778774,0.01399973,0.001698567,0.001928414,0.003916237,0.0005795845],"domain_scores_gemma":[0.7558495,0.2215568,0.01073852,0.006271915,0.004448634,0.001134598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002303881,0.001783793,0.9081673,0.000312841,0.001017705,0.0005040126,0.00287823,0.01416921,0.004365291,0.001899543,0.0008541156,0.06174401],"study_design_scores_gemma":[0.0003111937,0.00459663,0.7709567,0.0001008288,0.0002904384,0.000650835,0.002739626,0.2080696,0.004621954,0.005898712,0.001589248,0.0001742463],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9743651,0.00007009071,0.0231566,0.00009256324,0.0000172035,0.0002541939,0.0002677551,0.0001233386,0.001653269],"genre_scores_gemma":[0.980081,0.0000334584,0.01805895,0.00004134978,0.00001031478,0.0005973015,0.0005473144,0.0000431676,0.0005872476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02058629,"threshold_uncertainty_score":0.1088721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2663111200506548,"score_gpt":0.4952646775640436,"score_spread":0.2289535575133889,"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."}}