{"id":"W2169719505","doi":"10.1109/icsme.2014.26","title":"Why Do Automated Builds Break? An Empirical Study","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Leverage (statistics); Executable; Computer science; Software engineering; Breakage; Software; Empirical research; Work (physics); Engineering; World Wide Web; Operating system; 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":[0.0006327475,0.0001127832,0.0001273392,0.0001408862,0.00006616457,0.0002900863,0.001194675,0.00004929755,0.00005281414],"category_scores_gemma":[0.0003423879,0.0000919652,0.00002592986,0.0005700143,0.00001957617,0.0003470766,0.0003598043,0.0001433271,0.0001743099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003324114,"about_ca_system_score_gemma":0.00003088675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001238163,"about_ca_topic_score_gemma":0.00001534268,"domain_scores_codex":[0.998503,0.0001381149,0.0001393353,0.0004171038,0.0004741871,0.0003282878],"domain_scores_gemma":[0.9983118,0.0004166675,0.00001349025,0.0009716183,0.00008606421,0.000200387],"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":[0.000009929428,0.00190582,0.7597353,0.00002194858,0.00006913133,0.00008455627,0.003450409,0.002723326,0.0004630653,0.004355651,0.1818919,0.04528898],"study_design_scores_gemma":[0.0003916246,0.0005919198,0.3832989,0.00000351692,0.000001880654,0.00001538674,0.00002415556,0.6066293,0.0001696945,0.0001733738,0.008504937,0.00019527],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.491965,0.000005307905,0.5025143,0.0006551459,0.0001813392,0.0001483788,1.806839e-7,0.004048594,0.0004817308],"genre_scores_gemma":[0.9720037,1.666419e-7,0.0271867,0.0005734497,0.00006225151,0.00001549048,5.701937e-7,0.00001265624,0.0001450043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.603906,"threshold_uncertainty_score":0.3750232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02278950590193803,"score_gpt":0.3377818139732754,"score_spread":0.3149923080713374,"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."}}