{"id":"W4393754376","doi":"10.5281/zenodo.5838498","title":"Verification Witnesses from Verification Tools (SV-COMP 2022)","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01109187,0.002602689,0.0011318,0.003038101,0.001582928,0.006660074,0.002963899,0.002487095,0.2085676],"category_scores_gemma":[0.04126373,0.002125256,0.002016849,0.001717283,0.001259501,0.009304997,0.009570544,0.004298821,0.1257077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001592068,"about_ca_system_score_gemma":0.00396294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002512384,"about_ca_topic_score_gemma":0.002544666,"domain_scores_codex":[0.9863417,0.003767261,0.001286891,0.001457675,0.006208587,0.000937794],"domain_scores_gemma":[0.9790326,0.006514052,0.0007299797,0.007781023,0.005243358,0.0006989803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004409278,0.00007504242,0.0004511735,0.000692677,0.00006140721,0.000390994,0.0004980504,0.001866641,0.003845313,0.08328919,0.7407337,0.167655],"study_design_scores_gemma":[0.0001659656,0.00009013681,0.0003186303,0.0004365779,0.00002835821,0.0004965057,0.0001663332,0.01068852,0.01734639,0.05997607,0.9101869,0.00009955071],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.002144602,0.0006538284,0.6007331,0.002256585,0.002107685,0.0007161054,0.02538383,0.279671,0.08633331],"genre_scores_gemma":[0.09395882,0.001714113,0.3812833,0.002723739,0.001018662,0.002060784,0.1632981,0.1923511,0.1615914],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.2085676,"threshold_uncertainty_score":0.6977282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03973750652817714,"score_gpt":0.2620691346409862,"score_spread":0.2223316281128091,"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."}}