{"id":"W4391853530","doi":"10.1109/ms.2024.3366111","title":"The State of Documentation Practices of Third-Party Machine Learning Models and Datasets","year":2024,"lang":"en","type":"article","venue":"IEEE Software","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Documentation; Computer science; Software engineering; State (computer science); Software bug; Data science; Software; Knowledge management; Engineering management; Artificial intelligence; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.204897,0.0006513837,0.0009077945,0.01397754,0.003403927,0.01578577,0.005690611,0.002470809,0.003648602],"category_scores_gemma":[0.5293217,0.001944885,0.001069999,0.01334696,0.007636942,0.01656943,0.007922524,0.00494873,0.00303177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00719713,"about_ca_system_score_gemma":0.01524614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009981156,"about_ca_topic_score_gemma":0.004400819,"domain_scores_codex":[0.7906761,0.0873106,0.03442714,0.01638892,0.06806301,0.003134291],"domain_scores_gemma":[0.1698953,0.3897043,0.07108104,0.2507628,0.1143104,0.004246116],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006965995,0.0005587403,0.0991974,0.002657735,0.000251823,0.0003306991,0.02508322,0.004657495,0.007667445,0.09123004,0.03623543,0.7314333],"study_design_scores_gemma":[0.0003028669,0.0009818692,0.1253978,0.01661007,0.0003901518,0.00322293,0.03901932,0.03548034,0.05679723,0.1307187,0.5899565,0.001122232],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4635897,0.01212586,0.3947912,0.03898615,0.0007948753,0.001119812,0.007989603,0.01082587,0.06977695],"genre_scores_gemma":[0.7584095,0.005409968,0.2103736,0.004010761,0.0003431934,0.0009911074,0.008503459,0.003755632,0.00820282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.795103,"threshold_uncertainty_score":0.9805036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1339046038073511,"score_gpt":0.4107785703011077,"score_spread":0.2768739664937566,"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."}}