{"id":"W4415821354","doi":"10.1109/tse.2025.3627891","title":"Causes and Canonicalization of Unreproducible Builds in Java","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artifact (error); Java; Software; Taxonomy (biology); Focus (optics); Identification (biology); Software development; Legacy system","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"],"consensus_categories":[],"category_scores_codex":[0.004678768,0.0004881742,0.0004464856,0.006607022,0.001385077,0.001707962,0.001155439,0.0009705625,0.0009034631],"category_scores_gemma":[0.04797925,0.0005316551,0.0008102873,0.007904416,0.001474938,0.001798233,0.002419295,0.001266791,0.0005138615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063074,"about_ca_system_score_gemma":0.002586405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01060992,"about_ca_topic_score_gemma":0.01861179,"domain_scores_codex":[0.9867597,0.002722322,0.001899515,0.002736116,0.005092683,0.0007896214],"domain_scores_gemma":[0.8934863,0.04738366,0.02243669,0.0265146,0.008815219,0.001363497],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003105933,0.0001953716,0.8580597,0.0007333464,0.0001598044,0.001815995,0.004685452,0.006200124,0.004820467,0.006259733,0.01822709,0.09853227],"study_design_scores_gemma":[0.00005557826,0.0001526745,0.8515198,0.0004847338,0.0001816996,0.004607081,0.00405222,0.03133981,0.01548761,0.007555904,0.08443196,0.0001309382],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9569225,0.001548664,0.01702024,0.0006207261,0.00005610615,0.0001451956,0.01570824,0.003761194,0.004217247],"genre_scores_gemma":[0.9254166,0.001079937,0.01926955,0.0002455227,0.00005050439,0.0002426156,0.0507984,0.001135214,0.00176165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9953212,"threshold_uncertainty_score":0.02474397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01402969795472971,"score_gpt":0.2637907972674899,"score_spread":0.2497610993127602,"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."}}