{"id":"W4407384664","doi":"10.1007/978-3-031-79059-1_11","title":"Enhancing API Labelling with BERT and GPT: An Exploratory Study","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; Université du Québec à Rimouski","funders":"","keywords":"Labelling; Exploratory research; Computer science; Psychology; Sociology; Anthropology; Criminology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003376404,0.0005263541,0.0004720765,0.0008798452,0.0003479557,0.0008490604,0.0007182914,0.000290072,0.000006340538],"category_scores_gemma":[0.00002714212,0.0004329934,0.00002426231,0.0007282681,0.00005067648,0.004196738,0.0003280501,0.0005979897,0.000005415611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006987765,"about_ca_system_score_gemma":0.0004105104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005292046,"about_ca_topic_score_gemma":0.002232863,"domain_scores_codex":[0.9979458,0.00003189247,0.0006692216,0.0005112735,0.0005157584,0.0003260277],"domain_scores_gemma":[0.9980962,0.0001319174,0.0004987863,0.0005632565,0.0006314476,0.00007843159],"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":[0.0001028715,0.00009447394,0.0005551677,0.003275866,0.00007253096,0.00003437449,0.08802377,0.0130973,0.00004020764,0.006059089,0.00000250255,0.8886418],"study_design_scores_gemma":[0.02264873,0.003535058,0.007385737,0.08014164,0.001627512,0.0006267571,0.0129462,0.5028759,0.01639288,0.1915282,0.1381618,0.02212955],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003279695,0.00114196,0.9841536,0.0004420399,0.0002778859,0.0006893751,0.000003486691,0.0003256868,0.009686241],"genre_scores_gemma":[0.9145539,0.000198891,0.07558348,0.008352572,0.0004232796,0.000136963,0.0002365994,0.0001075233,0.0004067654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9112743,"threshold_uncertainty_score":0.9998122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00831088452925841,"score_gpt":0.2214782222410123,"score_spread":0.2131673377117539,"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."}}