{"id":"W1994492702","doi":"10.1145/1022494.1022542","title":"Continuous evolutionary one-step-ahead testing","year":2004,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Vendor; Computer science; Software engineering; Software release life cycle; Software; Software development; Backporting; Reliability engineering; Software reliability testing; Software construction; Engineering; Operating system; Business","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000420818,0.0004744783,0.0004378981,0.0004430733,0.0002156885,0.0002409097,0.002544383,0.0002189466,0.00001561753],"category_scores_gemma":[0.377578,0.0005443849,0.0001447918,0.001507361,0.00006133173,0.0008160793,0.001090445,0.000676846,0.0002782979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003963406,"about_ca_system_score_gemma":0.000270121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554223,"about_ca_topic_score_gemma":0.000002430574,"domain_scores_codex":[0.9966556,0.00002729181,0.000478158,0.0008612782,0.0008590408,0.001118598],"domain_scores_gemma":[0.8934875,0.1027883,0.0001275397,0.002602633,0.0004755202,0.0005184722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001437704,0.0003868685,0.8404095,0.0004742872,0.0001816815,0.0004431429,0.000694881,0.09566536,0.01046929,0.00759057,0.0007532604,0.04291677],"study_design_scores_gemma":[0.001634007,0.0004104932,0.9777309,0.000804728,0.00002924805,0.0003449075,0.000009509215,0.003507385,0.01020305,0.0006488427,0.00293453,0.001742456],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2297684,0.001194907,0.7609687,0.0005584685,0.0009048713,0.0003815236,0.00001409324,0.006201211,0.00000780821],"genre_scores_gemma":[0.552954,0.000005829375,0.4466417,0.00006124446,0.0001881981,0.00005587291,0.000008290834,0.00006160088,0.00002331121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3771572,"threshold_uncertainty_score":0.9997008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0294253370356965,"score_gpt":0.2481337484137635,"score_spread":0.218708411378067,"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."}}