{"id":"W4399531343","doi":"10.1145/3644815.3644963","title":"An Exploratory Study of Dataset and Model Management in Open Source Machine Learning Applications","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Computer science; TRACE (psycholinguistics); Key (lock); Focus (optics); Open source; Data modeling; Data science; Data mining; Predictive modelling; Database; Machine learning; Software; Operating system","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01061825,0.0004610783,0.0003671701,0.003360502,0.001620092,0.002950104,0.002383841,0.001101148,0.0006686787],"category_scores_gemma":[0.06853168,0.0005569498,0.0006177989,0.005336749,0.001424919,0.005815861,0.003002,0.002171436,0.0002942179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001629213,"about_ca_system_score_gemma":0.001741852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005256218,"about_ca_topic_score_gemma":0.007226538,"domain_scores_codex":[0.9898065,0.003445388,0.0009703696,0.001312899,0.003834956,0.000629879],"domain_scores_gemma":[0.9094509,0.05546119,0.007533179,0.01508972,0.01071111,0.001753828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.001710323,0.00414895,0.5160524,0.002624991,0.0003392502,0.006037612,0.06283449,0.02267384,0.04283701,0.01848901,0.01841608,0.303836],"study_design_scores_gemma":[0.0001339714,0.001972561,0.6110591,0.0008644653,0.0002903333,0.005085357,0.02734862,0.1869638,0.0529899,0.01385035,0.09903426,0.0004073686],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862804,0.0004943757,0.007746602,0.0004948316,0.00002523525,0.0002154682,0.001023617,0.001555116,0.002164325],"genre_scores_gemma":[0.9677917,0.0003423856,0.02468097,0.0001965508,0.0000320143,0.0002296297,0.004165764,0.0009886487,0.001572394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9976162,"threshold_uncertainty_score":0.05615538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04372501606269334,"score_gpt":0.3304473365670789,"score_spread":0.2867223205043855,"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."}}