{"id":"W4402050968","doi":"10.1007/s10664-024-10477-1","title":"On combining commit grouping and build skip prediction to reduce redundant continuous integration activity","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Commit; Computer science; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004091856,0.0002272743,0.000218564,0.0002598206,0.0001360865,0.0004275401,0.0002835311,0.0001068006,0.000001816526],"category_scores_gemma":[0.001886638,0.0002160379,0.00005028531,0.0006476004,0.00001930139,0.0003665714,0.000209444,0.0004533428,0.00001250672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001617147,"about_ca_system_score_gemma":0.00003338726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000451622,"about_ca_topic_score_gemma":9.587746e-7,"domain_scores_codex":[0.9986193,0.00004041895,0.0002165118,0.0005482761,0.0002648223,0.0003106851],"domain_scores_gemma":[0.9982319,0.001163444,0.00002986705,0.0003501548,0.00005221976,0.0001724111],"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":[0.00006890843,0.0002918411,0.0211615,0.000466823,0.0001411789,0.0002917821,0.006016362,0.01220791,0.008170389,0.01283322,0.08313455,0.8552155],"study_design_scores_gemma":[0.0003770095,0.001187178,0.0632141,0.003437925,0.00003258722,0.0002500824,0.00001013488,0.9047509,0.009865593,0.009819921,0.005994017,0.001060545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2164328,0.0001188449,0.7672226,0.0006548041,0.0006082682,0.0001535951,0.000003484806,0.01477496,0.00003064267],"genre_scores_gemma":[0.8669764,0.000003758717,0.1326013,0.0002013271,0.0001120936,0.00004348949,0.00000330488,0.00002867783,0.00002964728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.892543,"threshold_uncertainty_score":0.8809771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02111246643962035,"score_gpt":0.2853023932804197,"score_spread":0.2641899268407994,"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."}}