{"id":"W2945172560","doi":"10.1145/3314994.3325090","title":"A Mixed-Methods Study of Novice Programmer Interaction with Python Error Messages","year":2019,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Programmer; Computer science; Debugging; Usability; Python (programming language); Confusion; Consistency (knowledge bases); Feeling; Human–computer interaction; Multimedia; Mathematics education; Programming language; Psychology; Artificial intelligence; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02244177,0.0008015067,0.001455355,0.001390985,0.003029269,0.002491054,0.001684986,0.001596713,0.004648187],"category_scores_gemma":[0.03366647,0.001103245,0.0007098643,0.001081847,0.001584582,0.001863641,0.001603675,0.001727982,0.0008087087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001995648,"about_ca_system_score_gemma":0.004406623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003096405,"about_ca_topic_score_gemma":0.007367774,"domain_scores_codex":[0.9867052,0.008891061,0.00110518,0.00128405,0.001246926,0.0007675425],"domain_scores_gemma":[0.9461194,0.04133473,0.003777386,0.002601425,0.00453808,0.001628954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.01029642,0.1229977,0.1436034,0.005853869,0.0007180962,0.001661108,0.5186561,0.001125304,0.01239293,0.003040357,0.002615299,0.1770394],"study_design_scores_gemma":[0.007404201,0.2294223,0.3165758,0.001802356,0.0007272964,0.0008389275,0.4029381,0.00455262,0.008996164,0.004022828,0.02227557,0.0004437717],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932764,0.0001391299,0.002176158,0.00009771394,0.00002022911,0.003048426,0.0001848998,0.00001872647,0.001038292],"genre_scores_gemma":[0.9528022,0.0004317162,0.01588201,0.0006562269,0.00005219356,0.02365366,0.0003602983,0.00003823442,0.006123385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02244177,"threshold_uncertainty_score":0.1186849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02797544363982262,"score_gpt":0.3557687479176356,"score_spread":0.327793304277813,"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."}}