{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0136104,0.002504739,0.00112596,0.003301368,0.001519113,0.006495577,0.002887056,0.002395501,0.1966518],"category_scores_gemma":[0.04978785,0.002024926,0.001920603,0.001846556,0.001177754,0.009537105,0.009860712,0.004007536,0.1186324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001644572,"about_ca_system_score_gemma":0.004358534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002458381,"about_ca_topic_score_gemma":0.00252358,"domain_scores_codex":[0.9834784,0.004680998,0.001498634,0.001527846,0.0078468,0.0009673262],"domain_scores_gemma":[0.972934,0.00896065,0.0009510582,0.009386419,0.006949042,0.0008189124],"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":[0.0004740876,0.00008671099,0.0004593692,0.0008039377,0.00005445998,0.00030438,0.0004813567,0.001596916,0.003558279,0.06206587,0.7403641,0.1897504],"study_design_scores_gemma":[0.0001842528,0.0001145971,0.0004060002,0.0005151526,0.00002673459,0.0004670132,0.0001914153,0.01016401,0.01728058,0.04546712,0.9250856,0.00009747823],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.002797937,0.0008406028,0.5704935,0.002748636,0.002058624,0.001045972,0.03456714,0.2945407,0.09090681],"genre_scores_gemma":[0.08548754,0.00170933,0.4126537,0.002324161,0.0008667011,0.002502204,0.1967983,0.1674159,0.1302422],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.1966518,"threshold_uncertainty_score":0.6578659,"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."}}