{"id":"W4389159648","doi":"10.1145/3611643.3613082","title":"Towards Feature-Based Analysis of the Machine Learning Development Lifecycle","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Taxonomy (biology); Feature (linguistics); Software engineering; Trustworthiness; Feature engineering; Formal concept analysis; Software; Software development; Data science; Artificial intelligence; Machine learning; Deep learning; Programming language","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":[0.006163148,0.0009306681,0.0007738457,0.007043643,0.0009626091,0.004611095,0.001844311,0.001330515,0.001236045],"category_scores_gemma":[0.02531029,0.0007812395,0.002135014,0.003443254,0.001607943,0.006695635,0.002767926,0.002146257,0.0005255721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0024651,"about_ca_system_score_gemma":0.003271352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006022611,"about_ca_topic_score_gemma":0.0041179,"domain_scores_codex":[0.9954317,0.001461385,0.0004244431,0.0005712655,0.001732876,0.0003783281],"domain_scores_gemma":[0.9757556,0.01043291,0.003014574,0.004654534,0.00571399,0.0004285343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001801941,0.0004446114,0.04837243,0.0007926108,0.0001879054,0.0009670956,0.004969167,0.1067195,0.01107896,0.3012466,0.004916528,0.5201246],"study_design_scores_gemma":[0.00002281691,0.000139376,0.008393493,0.0003156504,0.00008835473,0.0003291206,0.001115015,0.6983347,0.009341822,0.2624786,0.01935617,0.00008493687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02089232,0.0002977045,0.9753209,0.0005319976,0.00001306055,0.00014775,0.0002421373,0.0008736746,0.001680514],"genre_scores_gemma":[0.1772998,0.0003435086,0.8201342,0.00008772653,0.00002669119,0.0003032631,0.0008959497,0.0002127878,0.0006960802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007043643,"threshold_uncertainty_score":0.03259426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01892595550722531,"score_gpt":0.2655430214331768,"score_spread":0.2466170659259515,"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."}}