{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004621676,0.001168225,0.001027786,0.001226283,0.0005424757,0.002137034,0.00231076,0.001777577,0.009334158],"category_scores_gemma":[0.07011808,0.0003752894,0.0004532861,0.0007687826,0.0004452101,0.002183194,0.001703877,0.00120476,0.002840601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007179945,"about_ca_system_score_gemma":0.001083489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001317795,"about_ca_topic_score_gemma":0.001094063,"domain_scores_codex":[0.9954529,0.002222916,0.0005357514,0.0008103056,0.0007437753,0.0002343386],"domain_scores_gemma":[0.9026374,0.0805969,0.003439327,0.003230442,0.00450087,0.005595072],"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":[0.08018408,0.06026069,0.03762739,0.002909752,0.0005209289,0.0005273596,0.006750045,0.0279892,0.0471477,0.001369673,0.006553796,0.7281594],"study_design_scores_gemma":[0.02620064,0.2720634,0.1839923,0.001398432,0.002933851,0.001568495,0.008468587,0.3213003,0.1498838,0.008554406,0.02287387,0.0007619348],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987912,0.0002171913,0.005624786,0.00009839646,0.00009270701,0.0005628203,0.0002397319,0.0005770319,0.004675307],"genre_scores_gemma":[0.97982,0.0001852778,0.0151275,0.00007948129,0.00004600765,0.0006373256,0.0007004496,0.00009350487,0.00331042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009334158,"threshold_uncertainty_score":0.03122586,"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."}}