{"id":"W2059210005","doi":"10.1145/944217.944243","title":"Evaluating modeling techniques based on models of learning","year":2003,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Domain (mathematical analysis); Grammar; Test (biology); Machine learning; Natural language processing; Mathematics; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001332994,0.00006900931,0.000119346,0.0000762102,0.000252827,0.00002018209,0.01178886,0.00003195035,0.000001284837],"category_scores_gemma":[0.005277208,0.00005369622,0.00008420258,0.0002478076,0.00004133927,0.0001210643,0.002919846,0.000243796,0.000001512371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002929915,"about_ca_system_score_gemma":0.00006769606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003647684,"about_ca_topic_score_gemma":8.829639e-7,"domain_scores_codex":[0.998754,0.0005287747,0.000276721,0.0001193927,0.0002242574,0.00009683602],"domain_scores_gemma":[0.9869987,0.0003875097,0.0002329123,0.01213932,0.0002273271,0.00001419048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.38957e-7,0.00003289904,0.0001440337,0.000008501338,0.000004721273,1.293215e-8,0.0003359154,0.6560422,0.002599179,0.3392359,0.000009959171,0.001585893],"study_design_scores_gemma":[0.00004272636,0.00004959558,0.000007259216,0.0002314745,0.000004009173,4.860482e-7,0.00008230824,0.9486596,0.01493817,0.03541225,0.0005187397,0.0000533798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0129978,0.0003154251,0.9678719,0.001850598,0.00007775332,0.0002431507,4.859461e-7,0.0001007216,0.01654214],"genre_scores_gemma":[0.6263448,0.000008092297,0.3734799,0.00001778812,0.000002805461,0.000009249593,2.218305e-7,0.000004496581,0.0001326124],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6133471,"threshold_uncertainty_score":0.9935578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1975873328404231,"score_gpt":0.372712511628928,"score_spread":0.1751251787885049,"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."}}