{"id":"W4362584426","doi":"10.1007/s10664-022-10282-8","title":"Towards a change taxonomy for machine learning pipelines","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; York University; Ansys (Canada); Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Metadata; Replicate; Pipeline (software); Taxonomy (biology); Implementation; Data science; Fork (system call); Source code; Information retrieval; World Wide Web; Software engineering; Programming language; Ecology","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":[0.00621377,0.001245824,0.001175708,0.008686212,0.003513082,0.00811958,0.003956741,0.004507366,0.007276356],"category_scores_gemma":[0.02582208,0.001512982,0.003594839,0.004998873,0.005092046,0.02120491,0.005503446,0.007333841,0.004135376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003141814,"about_ca_system_score_gemma":0.005410812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01167777,"about_ca_topic_score_gemma":0.01023537,"domain_scores_codex":[0.9932827,0.001467477,0.00104646,0.001569733,0.002078434,0.0005551683],"domain_scores_gemma":[0.9727721,0.007659595,0.001687973,0.007161902,0.009246711,0.001471739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001382553,0.0002886741,0.01228608,0.0005433715,0.00007400111,0.000479478,0.002974644,0.01668383,0.002797794,0.7312455,0.01314957,0.2193388],"study_design_scores_gemma":[0.00004303426,0.0001646883,0.002594586,0.000341714,0.00009271681,0.0005187377,0.00116122,0.2362532,0.003050321,0.6670912,0.08860309,0.00008555446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008185324,0.0003548082,0.9775223,0.00188782,0.0001111294,0.00058459,0.0006566226,0.002885682,0.00781175],"genre_scores_gemma":[0.1037508,0.0004567326,0.8860087,0.0004560165,0.00009677796,0.0005365134,0.002133831,0.0006065238,0.005954081],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01167777,"threshold_uncertainty_score":0.03286195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1089915916716536,"score_gpt":0.316721378863043,"score_spread":0.2077297871913895,"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."}}