{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008993364,0.00027109,0.00027655,0.0003236015,0.002753111,0.003345214,0.005615898,0.0001845302,0.008781776],"category_scores_gemma":[0.0008306828,0.0003136558,0.00007432442,0.000996368,0.0001374604,0.0004376995,0.005998566,0.0007591938,0.01739315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001783757,"about_ca_system_score_gemma":0.00002308288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004763733,"about_ca_topic_score_gemma":7.78278e-7,"domain_scores_codex":[0.9968003,0.0006071529,0.0004304485,0.001000336,0.0006744901,0.0004872427],"domain_scores_gemma":[0.9964908,0.00006741921,0.0002676734,0.002307288,0.0006195956,0.0002472119],"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":[0.000005319816,0.0001409383,3.46245e-8,0.0001146502,0.00003723623,0.00004926467,0.0001141587,0.00002036715,0.00003408352,0.001436761,0.9861566,0.01189051],"study_design_scores_gemma":[0.0002489994,0.00009363358,0.000007603797,0.00008279996,0.00001527328,0.0002213291,0.00003342556,0.0009037186,0.00004274082,0.00007419838,0.9979458,0.0003305024],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000005778238,0.0002026093,0.02035147,0.0008384312,0.0005497634,0.0003024063,0.9749937,0.0006573398,0.002098471],"genre_scores_gemma":[0.00008220453,0.000254879,0.001228354,0.0007281466,0.0003388551,4.571787e-8,0.9968063,0.0004711156,0.00009008766],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02181258,"threshold_uncertainty_score":0.9999316,"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."}}