{"id":"W2548701964","doi":"10.1145/2994291.2994294","title":"PredSym: estimating software testing budget for a bug-free release","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Overfitting; Symbolic execution; Regression testing; Software; Code (set theory); Software performance testing; Code coverage; Software bug; Concolic testing; Software testing; Programming language; Software engineering; Machine learning; Software system; Software construction; Artificial neural network","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":[0.002368492,0.001627662,0.0006436822,0.002449127,0.0002750283,0.0006933728,0.001132015,0.0006269604,0.00400711],"category_scores_gemma":[0.02299598,0.0005942182,0.0005287951,0.001017588,0.0003574977,0.001504903,0.0006827784,0.0007835318,0.001593008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007232433,"about_ca_system_score_gemma":0.00120463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003858386,"about_ca_topic_score_gemma":0.006137342,"domain_scores_codex":[0.9986986,0.0003023229,0.000107632,0.0003024913,0.0004739724,0.0001149542],"domain_scores_gemma":[0.9852962,0.009047364,0.002217036,0.001448299,0.00166565,0.0003254801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001450221,0.0004145775,0.1059746,0.001001226,0.0001885879,0.0003954526,0.0003800779,0.4098914,0.02104416,0.004305607,0.02881407,0.4261402],"study_design_scores_gemma":[0.00004821112,0.0002367009,0.01160371,0.00004753244,0.0000247438,0.000111677,0.00005202282,0.9731647,0.01077402,0.00111021,0.002795136,0.00003125011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4828615,0.0008648992,0.4080504,0.0004979846,0.0001077043,0.0003221233,0.01118104,0.09010438,0.00600988],"genre_scores_gemma":[0.6885052,0.0002293258,0.2956499,0.00007005076,0.00002622668,0.0003774406,0.01075085,0.002246173,0.00214472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00400711,"threshold_uncertainty_score":0.01340508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0332152410180936,"score_gpt":0.2673196379326332,"score_spread":0.2341043969145396,"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."}}