{"id":"W3216180498","doi":"10.1109/icsme52107.2021.00026","title":"Mining Historical Test Failures to Dynamically Batch Tests to Save CI Resources","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Weighting; Metric (unit); Batch processing; Test case; Constant (computer programming); Test (biology); Machine learning; Programming language; Operations management; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.003745043,0.002126416,0.001169775,0.003569592,0.000439343,0.00119023,0.002829337,0.000709035,0.001016904],"category_scores_gemma":[0.02243496,0.0007722669,0.0008414845,0.002477373,0.0005421824,0.002234129,0.001006334,0.001240872,0.0007697183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009092557,"about_ca_system_score_gemma":0.001625507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01043321,"about_ca_topic_score_gemma":0.01523048,"domain_scores_codex":[0.9972446,0.0005398484,0.0002437039,0.0009021083,0.0008603809,0.0002094595],"domain_scores_gemma":[0.9818757,0.007755905,0.003027522,0.0034846,0.003224065,0.0006321748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007697536,0.0006467736,0.2852485,0.0006763149,0.0004514435,0.0005245188,0.0004820497,0.3478287,0.01880217,0.002200838,0.01634697,0.3260219],"study_design_scores_gemma":[0.00006467517,0.0004413011,0.04003651,0.00005469567,0.0001214447,0.0002580551,0.0002055533,0.9394779,0.01209823,0.003394357,0.003792624,0.00005459675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7131076,0.001352793,0.2627072,0.0005673351,0.0001720666,0.0004032992,0.00538903,0.0133916,0.00290917],"genre_scores_gemma":[0.8868132,0.0002439467,0.1032366,0.0001248849,0.00004993521,0.0002605265,0.007694811,0.000513397,0.001062669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01043321,"threshold_uncertainty_score":0.02074498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01722203246024288,"score_gpt":0.2577121106951106,"score_spread":0.2404900782348678,"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."}}