{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001120625,0.0003712319,0.0003567985,0.0004718608,0.003863746,0.002584165,0.006561782,0.0002086001,0.09144902],"category_scores_gemma":[0.00172742,0.0004447142,0.000106095,0.001324047,0.0001661986,0.001074007,0.004967465,0.001279198,0.006195888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004987575,"about_ca_system_score_gemma":0.00002622917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001827723,"about_ca_topic_score_gemma":9.198478e-7,"domain_scores_codex":[0.9953129,0.001238443,0.0005403518,0.001309715,0.001104402,0.0004941642],"domain_scores_gemma":[0.9961697,0.0001518816,0.0005721901,0.002413778,0.0005033195,0.0001891222],"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":[0.00003233009,0.0001240197,3.017695e-7,0.00005420195,0.00005479647,0.0000207052,0.0002926486,0.001051951,0.000260395,0.00207025,0.9507709,0.04526754],"study_design_scores_gemma":[0.0003624297,0.0001291534,0.0001633055,0.00003103867,0.00003497267,0.00003442824,0.0001079352,0.002223028,0.00004768132,0.000293946,0.9961262,0.0004458219],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000100214,0.000228524,0.1528148,0.001042989,0.001306703,0.0008714375,0.8379512,0.001717562,0.003966524],"genre_scores_gemma":[0.001002775,0.0002890811,0.001436637,0.0001825336,0.0003746072,5.08692e-7,0.995642,0.000857935,0.0002139352],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1576908,"threshold_uncertainty_score":0.9998004,"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."}}