{"id":"W4223432363","doi":"10.1145/3524610.3529156","title":"Error identification strategies for Python Jupyter notebooks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Python (programming language); Computer science; Programming language; Exploratory data analysis; Software engineering; Data science; Data mining","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007307428,0.0001993633,0.0001875981,0.0002538103,0.0001237507,0.0008801369,0.002153955,0.00015378,0.0001316907],"category_scores_gemma":[0.0002026635,0.0002058582,0.0001234268,0.0001293545,0.00002476958,0.0002475482,0.002253325,0.0005885878,0.00004309872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001581359,"about_ca_system_score_gemma":0.0004015249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006398695,"about_ca_topic_score_gemma":0.000008402426,"domain_scores_codex":[0.9980609,0.00005280758,0.0002918372,0.0007560795,0.0005102134,0.0003281764],"domain_scores_gemma":[0.9977482,0.0005355749,0.00009152697,0.001419675,0.0001353402,0.00006970354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006022319,0.0003564163,0.001068773,0.00341119,0.0004144442,0.00006366269,0.009263071,0.1829127,0.008760987,0.6672185,0.07098117,0.05548884],"study_design_scores_gemma":[0.0009306798,0.0002848991,0.02563963,0.0001245656,0.00004620423,0.00001614258,0.0007227619,0.6832873,0.01045288,0.1922334,0.08389934,0.002362222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00683354,0.0000544181,0.9877555,0.000555709,0.002028357,0.0008179871,0.00002356065,0.001018687,0.0009122178],"genre_scores_gemma":[0.7180451,0.000008860533,0.2616422,0.0001664393,0.0003499266,0.003136159,0.0001831065,0.00009424215,0.01637403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7261134,"threshold_uncertainty_score":0.848718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06175773032543677,"score_gpt":0.3416812496562637,"score_spread":0.2799235193308269,"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."}}