{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001011667,0.0001232481,0.0001880517,0.0001144338,0.00006081656,0.000128188,0.0004233037,0.00003536384,0.00001708031],"category_scores_gemma":[0.00003532637,0.00008604091,0.00003564945,0.0003858952,0.00001604715,0.00037433,0.0001515633,0.0002724879,0.00002712656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001724606,"about_ca_system_score_gemma":0.00002325781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005478294,"about_ca_topic_score_gemma":0.00008461801,"domain_scores_codex":[0.9985564,0.000440704,0.0001909362,0.0003687174,0.0002376447,0.0002056309],"domain_scores_gemma":[0.9990366,0.0001728891,0.0001540987,0.0005140302,0.00007521265,0.00004715868],"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":[0.0000216492,0.0005815322,0.01897639,0.00002553354,0.00004543538,0.000002636232,0.009112159,0.0003610949,0.0002629325,0.0008234542,0.00003853134,0.9697487],"study_design_scores_gemma":[0.009634115,0.03037585,0.225001,0.0006664341,0.0002351337,0.0002801971,0.1521113,0.1295241,0.009239838,0.0001215721,0.4401858,0.002624606],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5722671,0.00001265897,0.4259835,0.0001630231,0.0002271631,0.0003081667,3.035079e-8,0.000271891,0.0007664552],"genre_scores_gemma":[0.639279,1.212052e-7,0.3600644,0.00001983369,0.000009706491,0.00001557999,3.279652e-7,0.000008032215,0.0006030001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.967124,"threshold_uncertainty_score":0.3508646,"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."}}