{"id":"W2527725345","doi":"10.82308/53701","title":"Cognitive assessment in a computer-based coaching environment in higher education : diagnostic assessment of development of knowledge and problem-solving skill in statistics","year":2007,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bayesian network; Bayesian statistics; Computer science; Machine learning; Domain knowledge; Artificial intelligence; Domain (mathematical analysis); Bayesian probability; Process (computing); Bayesian inference; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003048568,0.0002863973,0.0004637045,0.0006427015,0.0001456804,0.00003577938,0.0003174581,0.0001145462,0.00001176194],"category_scores_gemma":[0.0001304336,0.0003079055,0.00003860634,0.0004485028,0.00004819302,0.0003772564,0.0003051307,0.0006265587,0.000002822273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001236245,"about_ca_system_score_gemma":0.0002752446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002373884,"about_ca_topic_score_gemma":0.0004445818,"domain_scores_codex":[0.9968444,0.0004571324,0.001197307,0.0005975092,0.0004523101,0.0004514059],"domain_scores_gemma":[0.9973095,0.001739503,0.0004780116,0.0002304331,0.0001307948,0.0001117278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002080331,0.002574111,0.1278209,0.000629921,0.00004519536,0.00006002727,0.0005226222,0.007065542,0.004902552,0.3842336,1.926179e-7,0.4721246],"study_design_scores_gemma":[0.001422495,0.0002882703,0.9733052,0.00343184,0.00001302142,0.000004275322,0.0002752093,0.01003916,0.007322898,0.002234431,0.001130576,0.0005325899],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9416866,0.0001245464,0.05496362,0.00001151766,0.0003149895,0.0007940097,0.00002493974,0.00002442368,0.002055354],"genre_scores_gemma":[0.7968991,0.00001277915,0.2029092,0.00002438351,0.000009195873,0.00004910324,0.00001183896,0.00001897623,0.00006540338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8454843,"threshold_uncertainty_score":0.9999373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02649048259604153,"score_gpt":0.2892694912468863,"score_spread":0.2627790086508448,"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."}}