{"id":"W4416229447","doi":"10.1145/3776739","title":"An Empirical Analysis of Machine Learning Model and Dataset Documentation, Supply Chain, and Licensing Challenges on Hugging Face","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Documentation; License; Software; Face (sociological concept); Artificial neural network; Facial recognition system; Work (physics); Convolutional neural network","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":[0.0008451496,0.0001758851,0.0003737473,0.0007079229,0.0001902966,0.00004361941,0.0002124476,0.0001050419,0.000002656427],"category_scores_gemma":[0.0007998059,0.0001801925,0.00003655773,0.0004566601,0.000052309,0.0002494686,0.00004114378,0.0004058538,1.300747e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002030786,"about_ca_system_score_gemma":0.00001762124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004829037,"about_ca_topic_score_gemma":0.00001813678,"domain_scores_codex":[0.9986666,0.0003444689,0.0002190168,0.0004767683,0.0001042842,0.0001888972],"domain_scores_gemma":[0.9970806,0.002344473,0.00006289155,0.0003953785,0.00004093375,0.00007568564],"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":[0.00002057509,0.00001929035,0.0007685437,0.00004231432,0.0001924665,0.000001783954,0.001749232,0.8959204,0.0002617674,0.0007622337,0.000001850006,0.1002596],"study_design_scores_gemma":[0.0003057758,0.0001179144,0.005234146,0.00003576552,0.0002341637,0.000007943265,0.0001867839,0.9930756,0.0002466478,0.0002608703,0.000144757,0.0001496475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04019029,0.0006088026,0.9581064,0.0007492332,0.00008606957,0.00006919633,0.00003067216,0.0001573082,0.000002031748],"genre_scores_gemma":[0.4036867,0.000485183,0.59562,0.0001433599,0.000006179949,0.000005977446,0.00003028356,0.000009320796,0.00001292263],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3634964,"threshold_uncertainty_score":0.7348037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06670334465444491,"score_gpt":0.3676025793805503,"score_spread":0.3008992347261054,"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."}}