{"id":"W4400208339","doi":"10.1007/978-3-031-64302-6_11","title":"Evaluating the Effectiveness of Comparison Activities in a CTAT Tutor for Algorithmic Thinking","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; TUTOR; Artificial intelligence; Operations research; Human–computer interaction; Software engineering; Programming language; 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":[0.009076971,0.0003999667,0.0006253418,0.0006961903,0.000305674,0.0006639712,0.002613645,0.0002041583,0.000001195465],"category_scores_gemma":[0.0003947616,0.0002975176,0.0001774788,0.0005679505,0.0004946062,0.0003346332,0.0009589567,0.00137129,0.000002809966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003212455,"about_ca_system_score_gemma":0.0004244922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008388902,"about_ca_topic_score_gemma":0.00004971883,"domain_scores_codex":[0.9965718,0.0002691188,0.0005383663,0.001160349,0.0008966918,0.0005637208],"domain_scores_gemma":[0.9924092,0.006309488,0.0003042092,0.000819667,0.0001081875,0.00004920716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002124774,0.00002170281,0.00006815,0.0003359046,0.00001577218,0.000008024531,0.005935764,0.1349091,0.0001554512,0.02832715,7.975834e-7,0.8302009],"study_design_scores_gemma":[0.0002746607,0.0004655933,0.0001349901,0.00271318,0.00001540972,0.0000201889,0.00000292883,0.8684911,0.0006847113,0.1261152,0.0007167652,0.0003652679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001348237,0.00136182,0.9941043,0.0001997229,0.001791902,0.0008422859,0.000002536224,0.0001504893,0.0001987166],"genre_scores_gemma":[0.5418093,0.000004593134,0.4576721,0.00007436202,0.0002362879,0.0000598517,0.000002935928,0.00003629447,0.0001042162],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8298357,"threshold_uncertainty_score":0.9999477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04014915320833006,"score_gpt":0.3457887730391642,"score_spread":0.3056396198308341,"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."}}