{"id":"W4412704008","doi":"10.1145/3696630.3728523","title":"Learning to Edit Interactive Machine Learning Notebooks","year":2025,"lang":"en","type":"article","venue":"","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Machine learning; Natural language processing; Human–computer interaction; Programming language","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":[0.003069125,0.002646154,0.0009776331,0.002212859,0.0008888842,0.00353068,0.003172889,0.001313258,0.1801926],"category_scores_gemma":[0.05545329,0.001292169,0.001078435,0.001569437,0.0006102351,0.00443148,0.003749663,0.00301088,0.09130191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006794,"about_ca_system_score_gemma":0.001755735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001973218,"about_ca_topic_score_gemma":0.003870499,"domain_scores_codex":[0.9964519,0.0006235043,0.0003239063,0.0008915157,0.001412132,0.0002970455],"domain_scores_gemma":[0.9546931,0.02166977,0.001518473,0.01147991,0.008350313,0.002288369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006863917,0.0003106526,0.001392759,0.0007951891,0.00004552044,0.0004987183,0.0008205011,0.00199171,0.008257287,0.007404542,0.6675541,0.3102426],"study_design_scores_gemma":[0.000290726,0.0001994654,0.003739369,0.0004130975,0.00003950865,0.0006188112,0.0005019807,0.01544234,0.02334588,0.01060172,0.9446285,0.0001785553],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.01917483,0.0005425666,0.2700771,0.001544207,0.00180272,0.001367138,0.02298783,0.6139605,0.06854314],"genre_scores_gemma":[0.09873527,0.0008911925,0.4555273,0.002574991,0.0007613858,0.002931998,0.06142198,0.1832584,0.1938975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1801926,"threshold_uncertainty_score":0.6028043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00638469280281444,"score_gpt":0.2772177025428909,"score_spread":0.2708330097400764,"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."}}