{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02598007,0.001941712,0.0007592986,0.002337815,0.001652852,0.004436462,0.004120232,0.002486054,0.004261384],"category_scores_gemma":[0.2094996,0.001204799,0.0007767218,0.001144312,0.003013734,0.008037114,0.005697251,0.00249737,0.001133485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001608185,"about_ca_system_score_gemma":0.002695779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001179517,"about_ca_topic_score_gemma":0.001647469,"domain_scores_codex":[0.9672921,0.01850539,0.003032353,0.00478126,0.005257485,0.001131422],"domain_scores_gemma":[0.7080722,0.2277184,0.01946134,0.02805956,0.01420328,0.002485183],"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":[0.002931732,0.001453378,0.08589736,0.002695068,0.0001999619,0.006344643,0.2537242,0.01096567,0.04929097,0.03647914,0.01753823,0.5324796],"study_design_scores_gemma":[0.0008264339,0.004616853,0.08677582,0.005625156,0.0007049704,0.01743113,0.1079984,0.1896346,0.2356732,0.1099392,0.2388883,0.001885955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4513946,0.0003768474,0.5175455,0.001882917,0.000139286,0.001371077,0.0004300915,0.01821306,0.008646619],"genre_scores_gemma":[0.6528185,0.0002092239,0.3356394,0.0008318253,0.0000371292,0.00101101,0.0003760445,0.002447068,0.006629853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02598007,"threshold_uncertainty_score":0.1373974,"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."}}