{"id":"W4404860113","doi":"10.1007/s10664-024-10589-8","title":"Contrasting test selection, prioritization, and batch testing at scale","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Prioritization; Selection (genetic algorithm); Scale (ratio); Test (biology); Computer science; Regression testing; Reliability engineering; Engineering; Machine learning; Biology; Geography; Management science; Cartography; Operating system; Software","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":[0.000307279,0.0002041982,0.0001769458,0.000152602,0.0002234312,0.0003797149,0.0002365935,0.00009642054,0.000004386369],"category_scores_gemma":[0.005674148,0.0002071315,0.00003743677,0.001080181,0.0000261579,0.0003449387,0.0002575862,0.0002519389,0.00001659211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001454251,"about_ca_system_score_gemma":0.00005895402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001469796,"about_ca_topic_score_gemma":0.000001515828,"domain_scores_codex":[0.9986075,0.0000169943,0.0002644773,0.0005208901,0.0002209009,0.0003692019],"domain_scores_gemma":[0.9961893,0.003315818,0.0000303802,0.0001934014,0.000118573,0.0001525108],"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":[7.019847e-7,0.00002528777,0.9548622,0.0002186542,0.0000161561,0.00004476535,0.0004250544,0.001145268,0.0009108341,0.0001620083,0.009716628,0.03247243],"study_design_scores_gemma":[0.0001173214,0.0001045481,0.1222281,0.0005403875,0.00001506757,0.0005181963,0.000001187662,0.8676903,0.001044401,0.00207272,0.005173014,0.0004947563],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04334857,0.0006820197,0.9247217,0.0002865843,0.0002671727,0.0001091584,0.000002368202,0.03053448,0.00004793563],"genre_scores_gemma":[0.5154388,0.000004572682,0.4840932,0.0001159077,0.000190286,0.00002327883,0.000002233468,0.00003442233,0.00009726094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8665451,"threshold_uncertainty_score":0.8446575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01666081653409694,"score_gpt":0.2537672231562379,"score_spread":0.237106406622141,"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."}}