{"id":"W4393651954","doi":"10.5281/zenodo.5225650","title":"Copilot CWE Scenarios Dataset","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104789,0.002119467,0.0008107847,0.00358663,0.0008692507,0.001365416,0.002344809,0.002248814,0.01429942],"category_scores_gemma":[0.006057398,0.0004505975,0.001006236,0.004687999,0.0004784514,0.001209505,0.001720246,0.001743453,0.02466355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001610962,"about_ca_system_score_gemma":0.001868973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01810055,"about_ca_topic_score_gemma":0.03136386,"domain_scores_codex":[0.9985258,0.0002327052,0.0001622824,0.0003703421,0.0005311767,0.0001778534],"domain_scores_gemma":[0.9976981,0.000652609,0.0001744714,0.0006007393,0.000622766,0.0002512541],"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":[0.0001319804,0.00008558809,0.001696133,0.0007185073,0.00003996853,0.0001728131,0.00004462811,0.001594885,0.0004624171,0.0008625796,0.98832,0.005870606],"study_design_scores_gemma":[0.0002994387,0.00007460658,0.01042811,0.0003501754,0.00004952581,0.0004956534,0.0001771807,0.007868341,0.001850961,0.002554075,0.9757856,0.00006647377],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002743263,0.0002807263,0.0005098225,0.000242148,0.00005861145,0.00009126582,0.9912389,0.002295494,0.002539647],"genre_scores_gemma":[0.001880592,0.00005610055,0.0005681018,0.00005654854,0.000005717777,0.0001034386,0.9968317,0.00009754501,0.0004002777],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01810055,"threshold_uncertainty_score":0.04783636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05817534187296493,"score_gpt":0.2761713732383027,"score_spread":0.2179960313653377,"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."}}