{"id":"W2885174564","doi":"10.29007/qd4q","title":"Fine-Grained Test Minimization","year":2018,"lang":"en","type":"paratext","venue":"EasyChair preprint","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Test suite; Test (biology); Computer science; Code coverage; Test case; Minification; Test Management Approach; Test harness; Test script; Algorithm; Test method; Reliability engineering; Programming language; Software; Mathematics; Machine learning; Statistics; Engineering; Software system","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005553577,0.0004030064,0.0004603094,0.0001703131,0.0001852171,0.000201882,0.001777694,0.0004555835,0.001286966],"category_scores_gemma":[0.0002887505,0.0003442254,0.0002137425,0.000429766,0.0001094259,0.0002766818,0.0008528849,0.0003409339,0.03801478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001415999,"about_ca_system_score_gemma":0.000351241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004905186,"about_ca_topic_score_gemma":0.00001703059,"domain_scores_codex":[0.9971804,0.0001131413,0.0006160779,0.001198792,0.0004603726,0.0004311883],"domain_scores_gemma":[0.9964917,0.0001669226,0.0003790171,0.002447472,0.0003610545,0.0001537742],"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":[0.00001587198,0.0003526126,0.002413381,0.0005765492,0.0000741765,0.00000666966,0.001832146,0.009276932,0.00006551157,0.00042873,0.965961,0.01899639],"study_design_scores_gemma":[0.0008173455,0.0004127093,0.00703142,0.0007591537,0.000007671349,0.00005201482,0.00001968012,0.05404738,0.002102686,0.001041334,0.9323521,0.001356571],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004813946,0.0002730992,0.9131013,0.0007786693,0.008074163,0.0008532603,0.00002549785,0.0004411509,0.07597146],"genre_scores_gemma":[0.7326228,0.0001419963,0.02726141,0.000428369,0.00324545,0.0004350052,0.0001952765,0.00008760264,0.2355821],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8858399,"threshold_uncertainty_score":0.999901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01275836001757408,"score_gpt":0.2566982148709109,"score_spread":0.2439398548533369,"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."}}