{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004712248,0.00006550206,0.0001103894,0.000117246,0.0002444502,0.0004598381,0.0004125953,0.00001190322,0.0000219831],"category_scores_gemma":[0.002131593,0.0000377644,0.00003087677,0.0004406076,0.0001077039,0.0007675382,0.0003097543,0.00009658943,0.0000205825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006903447,"about_ca_system_score_gemma":0.00003103723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002057244,"about_ca_topic_score_gemma":0.00007909381,"domain_scores_codex":[0.9981804,0.0001643968,0.0003982807,0.0003479853,0.0007987336,0.000110207],"domain_scores_gemma":[0.9962966,0.002722211,0.0003800318,0.0004723872,0.0000961468,0.00003263808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005655418,0.00004654674,0.003502566,0.0001236596,0.00008937258,0.00001291087,0.005213867,0.05457469,0.0004264939,0.001034497,0.09207653,0.8428423],"study_design_scores_gemma":[0.000288147,0.0001125281,0.001705633,0.0001413491,0.00006178518,0.000008243625,0.001268086,0.7049164,0.001623985,0.08561949,0.2040692,0.0001851921],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7684511,0.004763406,0.221126,0.0009490456,0.002412285,0.0003678848,0.001278774,0.0001612903,0.0004902385],"genre_scores_gemma":[0.9956167,0.0001735448,0.002390809,0.00002161075,0.00001759006,0.000002709915,0.00006838125,0.000005295319,0.001703387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8426571,"threshold_uncertainty_score":0.443423,"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."}}