{"id":"W4389988565","doi":"10.1109/scam59687.2023.00018","title":"Do Code Quality and Style Issues Differ Across (Non-)Machine Learning Notebooks? Yes!","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Code refactoring; Code (set theory); Software quality; Quality (philosophy); Style (visual arts); Programming style; Programming language; Software; Software development","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":[0.0130569,0.0004687877,0.000423927,0.002743792,0.0006204309,0.00311388,0.000950927,0.0006840602,0.002499638],"category_scores_gemma":[0.187528,0.0004525414,0.0005998571,0.003295171,0.00209644,0.004481572,0.001659467,0.001453738,0.001061411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001266979,"about_ca_system_score_gemma":0.001276369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003012793,"about_ca_topic_score_gemma":0.004137662,"domain_scores_codex":[0.9861189,0.002230594,0.001435125,0.00272326,0.006848165,0.0006440164],"domain_scores_gemma":[0.7183767,0.1444718,0.07356199,0.01732215,0.04144764,0.00481972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007342016,0.0002499667,0.7938325,0.0009217749,0.0002840379,0.0003036472,0.01024231,0.001167121,0.004643384,0.001929659,0.007701682,0.1779897],"study_design_scores_gemma":[0.00004544036,0.0003188252,0.9761622,0.0004064515,0.00009066799,0.0004337362,0.004687352,0.001932802,0.004314799,0.002053099,0.009469759,0.0000847476],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794894,0.001160475,0.01005508,0.001388333,0.00011024,0.0001563009,0.001516249,0.001034525,0.005089407],"genre_scores_gemma":[0.9863927,0.0004579998,0.007360193,0.000555234,0.00005805359,0.0001340435,0.002052737,0.000752396,0.00223663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0130569,"threshold_uncertainty_score":0.06905228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05722378713182326,"score_gpt":0.385853588378114,"score_spread":0.3286298012462908,"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."}}