{"id":"W2898893292","doi":"10.1145/3236024.3236063","title":"Visual web test repair","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Focus (optics); Regression testing; Workflow; Pipeline (software); Test (biology); Test case; Artificial intelligence; Machine learning; Database; Software; Programming language; Regression analysis; Software development","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":[0.0002090846,0.00006778034,0.00006160753,0.00005692549,0.00009301574,0.00006681817,0.0004020948,0.00003248088,0.00003535899],"category_scores_gemma":[0.0005059351,0.00005517462,0.00003514456,0.0002625499,0.00005693755,0.0001493364,0.0002092479,0.00004714367,0.0003448114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001242737,"about_ca_system_score_gemma":0.0000443215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003370429,"about_ca_topic_score_gemma":0.000005361521,"domain_scores_codex":[0.9993668,0.00001363687,0.00009601465,0.0002341568,0.0001242549,0.0001651543],"domain_scores_gemma":[0.9991637,0.0002538276,0.00002343702,0.0004183902,0.0000879811,0.00005260123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.781622e-7,0.00009058701,0.03704933,0.000003783057,0.000004030653,0.00001286042,0.0001174087,6.993481e-8,0.0003394183,0.009272696,0.9241017,0.02900722],"study_design_scores_gemma":[0.0002403553,0.001396365,0.01378162,0.00005440182,0.000004736996,0.0001215533,0.000003087815,0.8455605,0.01037049,0.06818067,0.05976222,0.0005239822],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01023016,0.00002396202,0.7046105,0.0008189284,0.0003807464,0.00009381495,4.298925e-7,0.2129442,0.07089725],"genre_scores_gemma":[0.5223593,5.471073e-7,0.4758363,0.0007767985,0.0001148564,0.000003544775,1.39717e-7,0.00000390302,0.0009046078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8643395,"threshold_uncertainty_score":0.4431968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01627182758737435,"score_gpt":0.2877438271505185,"score_spread":0.2714719995631442,"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."}}