{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.003626961,0.00009571559,0.00013214,0.0002179152,0.003724148,0.0005269278,0.0005491677,0.00005055549,0.0002966841],"category_scores_gemma":[0.0183644,0.00007500703,0.00006326681,0.003695675,0.003347699,0.0005299672,0.00005994764,0.0001330052,0.00001932029],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008287401,"about_ca_system_score_gemma":0.01360049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008208981,"about_ca_topic_score_gemma":0.001040537,"domain_scores_codex":[0.9979206,0.0002446431,0.0002984685,0.0004519272,0.0007320958,0.0003522339],"domain_scores_gemma":[0.9960979,0.002145462,0.0002756332,0.0002242379,0.001112697,0.0001440445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000004141487,0.001355013,0.7011448,0.00003556116,0.00001779841,0.000001626457,0.1785937,0.005255236,0.009564762,0.07970776,0.002003996,0.02231562],"study_design_scores_gemma":[0.0002338257,0.00007874401,0.02393885,0.0005896419,0.0001301259,0.00001988647,0.7534992,0.1982644,0.006364035,0.01148286,0.004799208,0.0005992633],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9448637,0.001008735,0.01083018,0.005995671,0.002552381,0.0002525506,0.00001512568,0.0000416357,0.03444003],"genre_scores_gemma":[0.9896772,0.0000383002,0.00517638,0.0002102199,0.0002754916,0.0000120968,0.000005092261,0.000004245232,0.004600987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6772059,"threshold_uncertainty_score":0.9993646,"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."}}