{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006436497,0.0003015666,0.000312889,0.0004710841,0.0001479921,0.0001690815,0.0009382021,0.0001364283,0.00001513376],"category_scores_gemma":[0.006345161,0.0003006015,0.0001746041,0.001719993,0.00001772068,0.0004259918,0.0005361307,0.00043298,0.0001760032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001231944,"about_ca_system_score_gemma":0.00005840736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002792058,"about_ca_topic_score_gemma":0.000001475439,"domain_scores_codex":[0.9976963,0.00002616726,0.0002951347,0.0005889804,0.000442971,0.0009503819],"domain_scores_gemma":[0.9971014,0.001975043,0.00004015173,0.0004734985,0.0001243585,0.0002855908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004289324,0.0001792832,0.5485391,0.001337472,0.0002639356,0.0003237675,0.002583303,0.1615598,0.0005439431,0.001460425,0.02679804,0.256368],"study_design_scores_gemma":[0.00051198,0.0001376005,0.06699923,0.00006631934,0.000006814629,0.00001817302,0.000005791951,0.5910535,0.0004554311,0.0001055597,0.3400757,0.0005638945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01721358,0.000392377,0.9737093,0.000934197,0.0007699691,0.0006228355,0.00001249185,0.006337363,0.000007815785],"genre_scores_gemma":[0.5380636,0.00009906943,0.453638,0.0004486752,0.001962512,0.004346617,0.0001223806,0.0002577151,0.001061398],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5208501,"threshold_uncertainty_score":0.9999446,"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."}}