{"id":"W3092453472","doi":"10.1002/stvr.1751","title":"BUGSJS: a benchmark and taxonomy of JavaScript bugs","year":2020,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"European Social Fund; European Commission; Natural Sciences and Engineering Research Council of Canada; Advanced Remanufacturing and Technology Centre; National Research, Development and Innovation Office; Innovációs és Technológiai Minisztérium","keywords":"JavaScript; Computer science; Unobtrusive JavaScript; Benchmark (surveying); Unit testing; Software bug; Debugging; Taxonomy (biology); Programming language; Web application; Software; Software testing; Test case; Software engineering; Rich Internet application; World Wide Web; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005511987,0.0001535577,0.0002276603,0.00004720159,0.000141496,0.00007274273,0.0003338023,0.00008280217,0.000003231376],"category_scores_gemma":[0.008090468,0.0001421531,0.00003347906,0.0004528615,0.0002107048,0.0002230042,0.0002191219,0.0001603851,0.000002226435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001779868,"about_ca_system_score_gemma":0.00007726569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001374339,"about_ca_topic_score_gemma":4.456587e-7,"domain_scores_codex":[0.9986395,0.00008598289,0.0003574573,0.0005738101,0.0001719139,0.0001713254],"domain_scores_gemma":[0.9980181,0.0008358285,0.0001982041,0.0005232494,0.0002554432,0.0001691689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001791479,0.000119171,0.7038515,0.0005764411,0.00001329723,0.000003301,0.001568819,0.00003494488,0.0009246173,0.001602984,0.006655946,0.284631],"study_design_scores_gemma":[0.001239783,0.001254531,0.759297,0.0005059661,0.00007543569,0.00009819389,0.00009084362,0.145851,0.003799074,0.06938388,0.01696659,0.001437711],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1245939,0.0005449782,0.8630589,0.001984738,0.0001308656,0.000569618,0.000009754038,0.008673445,0.0004337709],"genre_scores_gemma":[0.5405484,0.00001007806,0.4591355,0.0002475098,0.00001903756,0.00002594316,0.000002179563,0.000005696434,0.000005655329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4159546,"threshold_uncertainty_score":0.9685631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05055143313862166,"score_gpt":0.2378494320064721,"score_spread":0.1872979988678504,"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."}}