{"id":"W4408204750","doi":"10.1007/s10664-025-10631-3","title":"Towards semantic versioning of open pre-trained language model releases on hugging face","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Face recognition and analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Software versioning; Computer science; Face (sociological concept); Natural language processing; Artificial intelligence; World Wide Web; Information retrieval; Linguistics; Programming language; Software","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0037157,0.001061168,0.0008340672,0.00119302,0.0007545041,0.003555245,0.002535978,0.00163029,0.005018873],"category_scores_gemma":[0.02468324,0.0009668671,0.00151219,0.0007559201,0.001200993,0.007616,0.004375065,0.003344444,0.002987406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003119,"about_ca_system_score_gemma":0.001896188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003942627,"about_ca_topic_score_gemma":0.005363886,"domain_scores_codex":[0.9963684,0.0008540732,0.0002883057,0.0009559777,0.001156052,0.0003772535],"domain_scores_gemma":[0.9841036,0.003669745,0.0005492181,0.009406694,0.00198646,0.0002842068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001537343,0.0007532489,0.01174076,0.0004245183,0.0002464202,0.0009877908,0.001914221,0.06764708,0.04992277,0.03441576,0.04387465,0.7865354],"study_design_scores_gemma":[0.0001049894,0.0002828017,0.003671792,0.0001307581,0.0001227506,0.0004034739,0.0004868047,0.854009,0.07072711,0.04890208,0.02103284,0.0001256297],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2080686,0.0005569404,0.6673707,0.0008211073,0.0008997053,0.0002518423,0.002527881,0.1100527,0.009450513],"genre_scores_gemma":[0.6994041,0.0002758164,0.2764629,0.000359563,0.0001464967,0.0001711599,0.008040638,0.008053001,0.007086404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.997464,"threshold_uncertainty_score":0.0196507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01979562248878209,"score_gpt":0.3129141107030443,"score_spread":0.2931184882142622,"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."}}