{"id":"W4392564511","doi":"10.1145/3626252.3630934","title":"Stump-the-Teacher: Using Student-generated Examples during Explicit Debugging Instruction","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Debugging; Algorithmic program debugging; Computer science; Programmer; Programming language; Mathematics education; Think aloud protocol; Usability; Psychology; Human–computer interaction","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":[0.002128193,0.0005548873,0.0004137677,0.0005032691,0.0005354196,0.001164065,0.001460729,0.001170152,0.002455244],"category_scores_gemma":[0.01790008,0.0003676386,0.0002291699,0.0002202625,0.0007616756,0.001569749,0.002333862,0.0009256683,0.0007559691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002838306,"about_ca_system_score_gemma":0.0006409877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004831782,"about_ca_topic_score_gemma":0.00174467,"domain_scores_codex":[0.9971994,0.001694704,0.0001156299,0.0003870018,0.0004231191,0.0001800948],"domain_scores_gemma":[0.988426,0.008357096,0.0008992011,0.001154756,0.0005354719,0.0006275972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00147812,0.004971026,0.04659497,0.001532503,0.00005695207,0.004830437,0.1277701,0.004639124,0.139839,0.003819488,0.005958169,0.6585101],"study_design_scores_gemma":[0.001037318,0.0231793,0.1428197,0.001939566,0.0003423416,0.02229969,0.07565837,0.06514943,0.4686033,0.009537591,0.1886926,0.0007408357],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9667621,0.0001457943,0.02664511,0.0001718111,0.00001809292,0.0002343625,0.00007702554,0.0007231545,0.005222691],"genre_scores_gemma":[0.9126668,0.0001524427,0.08383083,0.00007578896,0.000006103078,0.0001526839,0.0001736697,0.0000945517,0.002847198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002455244,"threshold_uncertainty_score":0.01125515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03757593771252991,"score_gpt":0.2978073105894859,"score_spread":0.260231372876956,"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."}}