{"id":"W4221142711","doi":"10.1145/3638243","title":"Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State of the Practice","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Université de Montréal; McMaster University; McGill University","keywords":"Workflow; Executable; Computer science; Domain (mathematical analysis); Software engineering; Subject-matter expert; Key (lock); Automation; Software; Data science; Domain engineering; Artificial intelligence; Knowledge management; Software development; Expert system; Component-based software engineering; Engineering; Programming language; Database","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010192,0.0001324482,0.000234162,0.0002327408,0.0004847324,0.0001016913,0.0008480439,0.00006034433,0.00002013035],"category_scores_gemma":[0.02420002,0.00007830077,0.0001310837,0.001346604,0.0001701626,0.00009486589,0.00008563215,0.0004338221,0.000009007726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001632405,"about_ca_system_score_gemma":0.00001881188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001671678,"about_ca_topic_score_gemma":0.000003317375,"domain_scores_codex":[0.9978744,0.0005723436,0.0003890063,0.0004531614,0.0004321939,0.000278827],"domain_scores_gemma":[0.9247397,0.07400774,0.0001505382,0.0009309833,0.0001223875,0.00004866646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006216094,0.00001523788,0.00004389421,0.000008456302,0.00006744925,0.000001344825,0.002282382,0.5468854,0.0001473872,0.006982749,0.0003075486,0.443196],"study_design_scores_gemma":[0.000559714,0.0001656314,0.002113741,0.0001021155,0.00008823622,0.00002885482,0.00425795,0.04056908,0.0007150109,0.05632703,0.8948032,0.0002694689],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02214534,0.0004279395,0.9732398,0.001518922,0.00223835,0.0002353621,0.00003465865,0.0001569977,0.000002582231],"genre_scores_gemma":[0.04718958,0.0001542569,0.9520117,0.0001253831,0.0000552808,0.00004327936,0.000001637539,0.00001798211,0.00040087],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8944956,"threshold_uncertainty_score":0.9840196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2062352037713582,"score_gpt":0.4093535291417279,"score_spread":0.2031183253703697,"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."}}