{"id":"W4393846738","doi":"10.5281/zenodo.7812451","title":"Dataset for \"Deep Dive into the Verifiability of Code Generated by GitHub Copilot\"","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Code (set theory); Computer science; Programming language","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":[0.001290526,0.004238026,0.001445764,0.003378308,0.001249556,0.001940888,0.004139076,0.003967992,0.02801296],"category_scores_gemma":[0.007681496,0.0007584341,0.001787667,0.003360998,0.0008768523,0.001377734,0.002682678,0.002652802,0.04946133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001899948,"about_ca_system_score_gemma":0.002760704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02220359,"about_ca_topic_score_gemma":0.04619187,"domain_scores_codex":[0.9979746,0.0003185543,0.0002292837,0.0004827912,0.0007400211,0.0002548806],"domain_scores_gemma":[0.9962832,0.001286662,0.0002949002,0.001111869,0.0007621718,0.0002611859],"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":[0.0001539641,0.00006246536,0.0007981038,0.001072475,0.00004896168,0.0001024657,0.00003182611,0.0009607631,0.0004560722,0.0007626752,0.9917018,0.003848545],"study_design_scores_gemma":[0.001070618,0.0001076254,0.007479108,0.0006100924,0.000093481,0.0003898773,0.0001206078,0.006264259,0.003062321,0.00508215,0.9756281,0.00009174235],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001135207,0.0002289482,0.0004145459,0.0001642958,0.00007286842,0.00004009237,0.9918209,0.004327146,0.001796044],"genre_scores_gemma":[0.001013192,0.00004753632,0.0005606423,0.0000744467,0.000006707658,0.00007108836,0.9976295,0.0001861216,0.0004108551],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02801296,"threshold_uncertainty_score":0.09371269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03581037201718835,"score_gpt":0.2719287974016264,"score_spread":0.2361184253844381,"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."}}