{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001478327,0.0001356495,0.0002409215,0.0002072551,0.0000686399,0.0001155707,0.000733683,0.00005344321,0.00001781066],"category_scores_gemma":[0.0005443104,0.0001273219,0.000106806,0.0006895301,0.00001107979,0.0002536874,0.0004196907,0.0001464232,0.000009706787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005765504,"about_ca_system_score_gemma":0.00006922193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003659803,"about_ca_topic_score_gemma":0.000001513576,"domain_scores_codex":[0.9990667,0.00002123187,0.0002084247,0.0002919036,0.0001998351,0.0002119016],"domain_scores_gemma":[0.9993372,0.0002007404,0.0000423801,0.0003034603,0.00004134219,0.00007489508],"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":[0.00001452607,0.0001283215,0.001791956,0.000186521,0.0001134518,0.00002117735,0.001577536,0.9558013,0.001951307,0.001295631,0.00159435,0.03552392],"study_design_scores_gemma":[0.0002763589,0.00002660983,0.002013001,0.0003090866,0.00001882048,0.000001027992,0.00005095245,0.9897111,0.007020039,0.0001463836,0.0002609787,0.0001656502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1039924,0.00009983841,0.8945722,0.0005347233,0.00007486744,0.00009909624,0.00000425935,0.000298949,0.0003236969],"genre_scores_gemma":[0.9309401,0.00000737257,0.0680889,0.00036293,0.00001142927,0.000009981058,0.000005358794,0.000009398897,0.000564567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8269477,"threshold_uncertainty_score":0.5192035,"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."}}