{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007724821,0.001459002,0.0006202083,0.009900055,0.001002397,0.001682161,0.002259229,0.001124907,0.000761656],"category_scores_gemma":[0.03974611,0.0005094592,0.0009711666,0.005282644,0.001155098,0.001973644,0.00227933,0.001240978,0.0004992518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001320001,"about_ca_system_score_gemma":0.002271777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006062353,"about_ca_topic_score_gemma":0.007132469,"domain_scores_codex":[0.9837818,0.003243753,0.002657262,0.001871558,0.007562133,0.0008834231],"domain_scores_gemma":[0.9476385,0.02349555,0.007570923,0.005881681,0.01366854,0.001744751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00150651,0.001861831,0.3265269,0.01015915,0.0006476183,0.002037836,0.005082357,0.07144265,0.04694578,0.01485986,0.07948637,0.4394431],"study_design_scores_gemma":[0.0004988544,0.003759026,0.315825,0.002588079,0.0005398901,0.004619811,0.003468318,0.4382162,0.08348332,0.02421858,0.1221908,0.0005920086],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.836064,0.006620603,0.09647378,0.001195072,0.0003905655,0.001358185,0.0226648,0.02722185,0.008011132],"genre_scores_gemma":[0.7861221,0.00161171,0.1481392,0.0003620574,0.0001119821,0.001365444,0.05682262,0.003329488,0.002135347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009900055,"threshold_uncertainty_score":0.04085326,"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."}}