{"id":"W4415064809","doi":"10.1016/j.jss.2025.112758","title":"A systematic literature review of software engineering research on Jupyter notebook","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Education and Learning Interventions","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Documentation; Code refactoring; Workflow; Code review; USable; Software; Social software engineering; Leverage (statistics); Software development; IBM","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002137412,0.00008759106,0.0003959943,0.00046545,0.00007588616,0.00016678,0.0003872715,0.00005867501,0.000005122182],"category_scores_gemma":[0.001908786,0.00006224619,0.0001460742,0.0005090529,0.00001666508,0.0001833721,0.0000611689,0.0004035365,0.000003930397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005125034,"about_ca_system_score_gemma":0.0001148463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002806653,"about_ca_topic_score_gemma":1.919673e-7,"domain_scores_codex":[0.9984024,0.0002776911,0.0006976349,0.000117384,0.0003794385,0.0001254317],"domain_scores_gemma":[0.9977794,0.0006049686,0.0003278591,0.0002987189,0.0009200837,0.00006897376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000009511573,0.0001801753,0.002152294,0.9274536,0.0002821383,0.00006831786,0.002722681,0.000335025,0.00003256977,0.03082409,0.03479241,0.001147139],"study_design_scores_gemma":[0.000197196,0.000197638,0.001577132,0.9893679,0.00002869971,0.0002167699,0.0001711846,0.0003778875,0.00001463755,0.00006479865,0.007699861,0.00008628621],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.004599015,0.6587979,0.3306958,0.002003504,0.002758721,0.0008309677,0.000005906705,0.00007497984,0.000233144],"genre_scores_gemma":[0.8057277,0.06163739,0.08901883,0.003185473,0.001195491,0.0002505607,0.000008488833,0.00009553267,0.0388805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8011287,"threshold_uncertainty_score":0.2538326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03094170045877877,"score_gpt":0.3461136380485219,"score_spread":0.3151719375897431,"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."}}