{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005312072,0.0001998815,0.0001895958,0.000109741,0.0002418382,0.0001597188,0.001402673,0.00007670718,0.0000064201],"category_scores_gemma":[0.02267628,0.0001345048,0.00007520107,0.0003250094,0.00004871185,0.000471132,0.0005739405,0.00007236715,0.00002392739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005565228,"about_ca_system_score_gemma":0.0001153948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006157749,"about_ca_topic_score_gemma":0.000002526664,"domain_scores_codex":[0.9984019,0.00003417817,0.0003069839,0.0005520746,0.0002366365,0.0004681693],"domain_scores_gemma":[0.9943554,0.00383608,0.0001452972,0.001235514,0.0002835285,0.0001441881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008295007,0.00006706833,0.01466951,0.00007886101,0.00001373742,0.0000151866,0.0001388849,0.00003473047,0.0007183742,0.005513288,0.1691179,0.8096241],"study_design_scores_gemma":[0.001104009,0.000442686,0.00127379,0.0007052256,0.00001501111,0.0001141423,0.000001918573,0.2332441,0.004184469,0.7567669,0.001461423,0.0006863291],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001560784,0.0000268484,0.9665644,0.001289823,0.0002276386,0.0002949569,0.000008706147,0.0294646,0.0005622404],"genre_scores_gemma":[0.05087468,3.819763e-7,0.9477662,0.0004582057,0.0001507141,0.0001412471,9.501465e-7,0.00002617019,0.0005814732],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8089378,"threshold_uncertainty_score":0.9855561,"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."}}