{"id":"W4401635770","doi":"10.1145/3688841","title":"An Exploratory Study on Machine Learning Model Management","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Concordia University","funders":"","keywords":"Documentation; Computer science; Software versioning; Software engineering; Automation; Code refactoring; Knowledge management; Data science; Process management; Software; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001360673,0.000255229,0.0002376097,0.0007083096,0.0001407631,0.0001354829,0.0006239156,0.00009708181,0.000006887542],"category_scores_gemma":[0.0004348053,0.0002503399,0.00006184314,0.0005137897,0.00002062236,0.0002878561,0.00004050589,0.0007842203,0.0000242275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006959657,"about_ca_system_score_gemma":0.00002554512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005321524,"about_ca_topic_score_gemma":0.000001960427,"domain_scores_codex":[0.9981838,0.0002753536,0.0001951844,0.0006973616,0.0002736287,0.0003746533],"domain_scores_gemma":[0.9962017,0.002740029,0.00001267533,0.0008460813,0.00002889931,0.0001706328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001515388,0.0001459748,0.0001228818,0.00009308777,0.0001335559,0.000116499,0.002682626,0.8539284,0.0002358449,0.001107948,0.00000975748,0.1414083],"study_design_scores_gemma":[0.0004725548,0.001260047,0.001207301,0.00009623895,0.00004896882,0.0000491216,0.0002287611,0.993506,0.0009337136,0.0005815494,0.001144447,0.0004713199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04163521,0.0003172697,0.9546192,0.00007891611,0.0006385975,0.0002250108,0.000004264713,0.002476974,0.000004500735],"genre_scores_gemma":[0.4782219,0.00006894397,0.5213235,0.00003292789,0.00002606967,0.0001298307,0.000001661036,0.00004285742,0.0001523135],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4365867,"threshold_uncertainty_score":0.9999949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1074396069106475,"score_gpt":0.3519211356913123,"score_spread":0.2444815287806648,"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."}}