{"id":"W4393699878","doi":"10.5281/zenodo.4459196","title":"Verification Witnesses from Verification Tools (SV-COMP 2021)","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Verification; Programming language; Software","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008326769,0.0003792917,0.0003935943,0.0003513159,0.002370291,0.003766041,0.004922278,0.0002946918,0.01171513],"category_scores_gemma":[0.00240328,0.0004432212,0.0001122549,0.001240492,0.000172216,0.001097589,0.003398413,0.000993847,0.0121277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003371078,"about_ca_system_score_gemma":0.00003327127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001360682,"about_ca_topic_score_gemma":0.00000123572,"domain_scores_codex":[0.9956744,0.001057772,0.0005473634,0.001346887,0.0008868836,0.0004867335],"domain_scores_gemma":[0.9956586,0.000149305,0.0004999115,0.002539914,0.0009448969,0.000207393],"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":[0.00001893796,0.0001189848,3.105222e-7,0.00006525405,0.00006291209,0.0000322376,0.0002147601,0.0005840038,0.0004218631,0.00127819,0.9355085,0.06169397],"study_design_scores_gemma":[0.0003418916,0.00007046235,0.0001858167,0.0001031237,0.00003837312,0.00003540675,0.00009375436,0.002450749,0.0001525587,0.0001950612,0.99589,0.0004427838],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0000954082,0.0003167064,0.293997,0.001171632,0.001167895,0.000649457,0.6971592,0.001012114,0.004430584],"genre_scores_gemma":[0.001224865,0.0004117445,0.003761638,0.0001434799,0.0006728589,2.393645e-7,0.9928418,0.0007589576,0.0001844605],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2956826,"threshold_uncertainty_score":0.9998019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04083143964140681,"score_gpt":0.2637057737441831,"score_spread":0.2228743341027763,"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."}}