{"id":"W2549749398","doi":"10.14288/1.0319084","title":"A study of the influence of assertions and mutants on test suite effectiveness","year":2016,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Suite; Test suite; Test (biology); Computer science; Biology; Test case; History; Archaeology","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":[0.0002384693,0.00002748462,0.0001504253,0.00003467856,0.0001116459,0.00001990522,0.0005333212,0.00003292233,7.575239e-7],"category_scores_gemma":[0.0003789047,0.00005302619,0.00003370193,0.000316865,0.0001864276,0.0001963811,0.0002763,0.00004501933,4.99802e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022212,"about_ca_system_score_gemma":0.00003804385,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01836198,"about_ca_topic_score_gemma":0.01131695,"domain_scores_codex":[0.9993342,0.0000941122,0.00008131627,0.0002166469,0.0001832118,0.00009055217],"domain_scores_gemma":[0.9985803,0.0006858123,0.0001301386,0.0003971291,0.0001753845,0.00003121629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003568988,0.0003674889,0.8392982,0.00003546729,0.0000133915,0.0000162495,0.0003012927,0.000005941472,0.002210771,0.000005672501,0.00007622799,0.1576657],"study_design_scores_gemma":[0.0004901951,0.0003980357,0.9969168,0.0005857575,0.00001001013,0.00001785659,0.00004497856,0.0000427973,0.00004534083,0.001385923,0.000001017795,0.00006131318],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979131,0.000006598085,0.001518889,0.00002500396,0.00002247882,0.0002144524,0.00001926553,0.0002415609,0.00003865405],"genre_scores_gemma":[0.9992767,0.000004294877,0.0006878899,0.000006275543,0.000001594878,5.990542e-7,5.650893e-8,0.00000300624,0.00001960057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1576185,"threshold_uncertainty_score":0.9881749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009772553224793704,"score_gpt":0.1978724058906307,"score_spread":0.188099852665837,"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."}}