{"id":"W7133004228","doi":"","title":"PathDiff: Systematic Differential Testing Using Symbolic Analysis","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Fuzz testing; Path (computing); Symbolic execution; Differential (mechanical device); Process (computing); Software bug; Software","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001285603,0.001134523,0.002481416,0.002078983,0.001714159,0.001199514,0.002670642,0.0004234638,0.00042225],"category_scores_gemma":[0.003281245,0.001191129,0.0009575696,0.007954816,0.00007982853,0.000270181,0.0009022962,0.001211507,0.00003021262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005852068,"about_ca_system_score_gemma":0.0005796166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004476783,"about_ca_topic_score_gemma":0.00005170018,"domain_scores_codex":[0.9923875,0.001146584,0.001590966,0.001923421,0.001826677,0.00112484],"domain_scores_gemma":[0.9917157,0.002473754,0.002347902,0.002540418,0.0005964267,0.0003257834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002817518,0.004592189,0.05076062,0.30843,0.02844489,0.00432831,0.5066245,0.04916466,0.01602693,0.006018596,0.00281076,0.02251677],"study_design_scores_gemma":[0.0002213026,0.0002088829,0.002467963,0.007797608,0.007660028,0.0001491393,0.001360243,0.9772751,0.0002074909,0.001137595,0.000004372322,0.001510327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4777736,0.002016639,0.5009101,0.00003806973,0.002599729,0.001856438,0.00002017074,0.01382033,0.0009649399],"genre_scores_gemma":[0.9231466,0.000015792,0.07382227,0.00006217824,0.0002214331,0.0002674863,0.0002159137,0.0001308193,0.002117503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9281104,"threshold_uncertainty_score":0.9998373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06123085727894456,"score_gpt":0.3772592000803296,"score_spread":0.3160283428013851,"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."}}