{"id":"W4405602578","doi":"10.1109/scam63643.2024.00014","title":"Breaking-Good: Explaining Breaking Dependency Updates with Build Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Sarah Scaife Foundation","keywords":"Computer science; Dependency (UML); Artificial intelligence","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":[0.0005195033,0.0002093151,0.0002887066,0.0004124872,0.0001896824,0.0006173993,0.0007309291,0.00008339817,0.0001118325],"category_scores_gemma":[0.00001589415,0.0001338774,0.0001682812,0.002484645,0.00003814322,0.001164649,0.0002201391,0.0001902061,0.0001459716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006149368,"about_ca_system_score_gemma":0.0001093102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003663953,"about_ca_topic_score_gemma":0.0001920721,"domain_scores_codex":[0.9980761,0.00005272933,0.0003187359,0.000713805,0.0004551564,0.0003834819],"domain_scores_gemma":[0.9987754,0.0001979865,0.00005945619,0.0007840149,0.00008540805,0.00009773888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002392805,0.0001480428,0.6391278,0.0005203839,0.002751966,0.0004503802,0.006516052,0.005295566,0.0002337146,0.1333956,0.001026315,0.2105103],"study_design_scores_gemma":[0.0005946455,0.00038642,0.05605553,0.0006845468,0.0008290965,0.0005553355,0.0006374675,0.9089528,0.003632262,0.00343737,0.02255848,0.001676042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1451532,0.0004418029,0.843587,0.0006587203,0.0004341074,0.0001354894,0.000001897784,0.001428531,0.008159233],"genre_scores_gemma":[0.9642718,0.00001152258,0.03512377,0.0001462616,0.00008988199,0.00002140224,0.000004305866,0.00001305799,0.0003179729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9036573,"threshold_uncertainty_score":0.5953596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005991379407993013,"score_gpt":0.2386922133698901,"score_spread":0.2327008339618971,"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."}}