{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003078838,0.001886384,0.0009166075,0.004406514,0.000550651,0.00232436,0.002988346,0.001490081,0.01238341],"category_scores_gemma":[0.02772626,0.000784068,0.001003672,0.001629982,0.0007960112,0.002310633,0.002660754,0.001353569,0.004496369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007946308,"about_ca_system_score_gemma":0.0009480836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002702618,"about_ca_topic_score_gemma":0.002633987,"domain_scores_codex":[0.9966504,0.0009045973,0.0002808872,0.0006542132,0.001286535,0.0002233437],"domain_scores_gemma":[0.9727692,0.009643225,0.003058804,0.00978168,0.004082157,0.0006650574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007905757,0.0005843497,0.01138277,0.001115396,0.0001789905,0.001339466,0.00134586,0.02306915,0.03973277,0.00551497,0.07089002,0.8440557],"study_design_scores_gemma":[0.0004314879,0.001551143,0.03259565,0.0008627733,0.0002553764,0.005956083,0.001735735,0.5257086,0.1971435,0.02514525,0.2082517,0.000362862],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06333788,0.0009371378,0.6231464,0.0006594399,0.0003030234,0.001118895,0.002932551,0.290402,0.01716264],"genre_scores_gemma":[0.5418953,0.0006184728,0.4114246,0.0007017103,0.0001576173,0.0007593436,0.008689772,0.01643623,0.01931702],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01238341,"threshold_uncertainty_score":0.0414266,"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."}}