{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.02200068,0.000926572,0.0008632117,0.002928562,0.001638146,0.002712341,0.002220675,0.00206831,0.003901975],"category_scores_gemma":[0.09920307,0.000399845,0.001004014,0.004302874,0.001962241,0.006117787,0.002350221,0.003338382,0.00189582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001696646,"about_ca_system_score_gemma":0.001447276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007105748,"about_ca_topic_score_gemma":0.009163543,"domain_scores_codex":[0.9883373,0.006216493,0.0007771921,0.001665765,0.002502224,0.0005010577],"domain_scores_gemma":[0.8723578,0.09026811,0.006236547,0.02272783,0.007201672,0.001208024],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001622087,0.001792738,0.4494932,0.00145356,0.0006928844,0.001341909,0.002083972,0.1727332,0.001662566,0.02349065,0.1538388,0.1897945],"study_design_scores_gemma":[0.0002914403,0.0009366572,0.1778945,0.0009054098,0.000307321,0.002608119,0.004312743,0.6745523,0.006165662,0.03982922,0.09191566,0.0002809862],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9438133,0.003158762,0.02036923,0.003306196,0.0002566336,0.0001784329,0.01921704,0.001675615,0.008024722],"genre_scores_gemma":[0.9308812,0.0006181882,0.01305128,0.0005018708,0.0001085292,0.0001601656,0.05199249,0.0003417178,0.002344563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9977793,"threshold_uncertainty_score":0.1163521,"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."}}