{"id":"W4293097939","doi":"10.1145/3478432.3499048","title":"Using Deep Learning to Localize Errors in Student Code Submissions","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 53rd ACM Technical Symposium on Computer Science Education V. 2","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Python (programming language); Computer science; Deep learning; Transfer of learning; Artificial intelligence; Coding (social sciences); Machine learning; Metric (unit); Natural language processing; Programming language; Statistics","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":[0.00470404,0.001356815,0.0006030202,0.002273902,0.0004757865,0.001902888,0.001270511,0.0012099,0.001833535],"category_scores_gemma":[0.04615768,0.0003230587,0.0003799872,0.001416486,0.000809364,0.001869868,0.001863855,0.002188877,0.001430735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009007513,"about_ca_system_score_gemma":0.00140907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00515588,"about_ca_topic_score_gemma":0.008365607,"domain_scores_codex":[0.9959797,0.001455855,0.0002308815,0.0008143609,0.001123002,0.0003962611],"domain_scores_gemma":[0.9626125,0.0220999,0.005207356,0.002983513,0.005542133,0.001554625],"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":[0.001921795,0.001204132,0.1836846,0.0007258331,0.0002574548,0.001015472,0.002537303,0.1651985,0.03047718,0.002451886,0.02423838,0.5862875],"study_design_scores_gemma":[0.00004768824,0.0005648714,0.03106695,0.000118338,0.00004108236,0.0003241981,0.0007042329,0.9176674,0.03842261,0.006167028,0.004779228,0.0000964249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8326469,0.0006255353,0.1430431,0.001250692,0.0003783506,0.0001040874,0.001465038,0.01563573,0.004850454],"genre_scores_gemma":[0.9706342,0.00006791554,0.02563856,0.0001230371,0.00002877931,0.00002616268,0.001001742,0.000437371,0.002042233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00515588,"threshold_uncertainty_score":0.02487767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02324682460761803,"score_gpt":0.3317174811870447,"score_spread":0.3084706565794267,"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."}}