{"id":"W4411271466","doi":"10.1109/msr66628.2025.00075","title":"CoUpJava: A Dataset of Code Upgrade Histories in Open-Source Java Repositories","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computer science; Java; Upgrade; Open source; Code (set theory); Source code; Programming language; Operating system; Database; World Wide Web; Software; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.001979856,0.001264686,0.0007563236,0.007238237,0.0009849051,0.001589911,0.002169144,0.002167419,0.001578774],"category_scores_gemma":[0.01558207,0.0006052947,0.001227579,0.006607297,0.0007319312,0.002092125,0.002147548,0.001875547,0.002958938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001007387,"about_ca_system_score_gemma":0.001528405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01199319,"about_ca_topic_score_gemma":0.0254814,"domain_scores_codex":[0.995796,0.0006411397,0.0004898161,0.00128735,0.001431995,0.0003537397],"domain_scores_gemma":[0.9877935,0.003549804,0.001396736,0.003643232,0.002897704,0.0007190517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001458633,0.0008917621,0.2067399,0.004392099,0.0007514906,0.002011274,0.001930457,0.01712699,0.01602639,0.004197142,0.5679237,0.1765501],"study_design_scores_gemma":[0.0003547946,0.0004418266,0.3736341,0.0006885075,0.0003061415,0.002578141,0.001092766,0.04148353,0.01231427,0.00444667,0.5623113,0.0003480281],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2476871,0.004812697,0.008547114,0.0009091213,0.0004068712,0.0002987958,0.7141512,0.01689877,0.006288262],"genre_scores_gemma":[0.06761403,0.0004741273,0.01030697,0.0002090212,0.00005459772,0.0002502546,0.9188364,0.0007299982,0.001524535],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01199319,"threshold_uncertainty_score":0.02384681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01965083016863603,"score_gpt":0.3051021555740446,"score_spread":0.2854513254054086,"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."}}