{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002706078,0.0001800139,0.000224466,0.0001615431,0.0001393187,0.0002841689,0.000914292,0.00007866266,0.00002663153],"category_scores_gemma":[0.004875056,0.0001663127,0.00006211333,0.0009823113,0.00001400581,0.0001093079,0.0008084114,0.0001319596,0.0001205477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002812856,"about_ca_system_score_gemma":0.00009829146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003407252,"about_ca_topic_score_gemma":0.0001690292,"domain_scores_codex":[0.9982184,0.00005249186,0.0002735976,0.0006732874,0.0003869746,0.0003952307],"domain_scores_gemma":[0.9971243,0.001436141,0.00004093181,0.0008329297,0.0002309361,0.0003348122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006109327,0.0002434662,0.04539261,0.00002121118,0.00001304807,0.0003817237,0.002568588,0.00008087666,0.00493711,0.002920994,0.8318794,0.1115549],"study_design_scores_gemma":[0.0006076609,0.002069679,0.07470988,0.0007188399,0.00003354979,0.000696435,0.0001260556,0.04550884,0.01348003,0.02682339,0.8323408,0.002884807],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03617683,0.0000787919,0.9060878,0.03590096,0.0003188963,0.0001683363,0.000002107253,0.01504754,0.006218697],"genre_scores_gemma":[0.2825761,4.906063e-7,0.7113521,0.003081001,0.00008117026,0.00002244545,9.239656e-7,0.00001396239,0.002871852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2463992,"threshold_uncertainty_score":0.6782033,"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."}}