{"id":"W4393610034","doi":"10.5281/zenodo.10460738","title":"Are Prompt Engineering and TODO Comments Friends or Foes? An Evaluation on GitHub Copilot","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Aeronautics; Computer security; Engineering","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":[0.008846716,0.004926373,0.002657576,0.003022922,0.001791376,0.003185094,0.004448094,0.003507946,0.078335],"category_scores_gemma":[0.02777299,0.00128532,0.002951354,0.003335505,0.001202531,0.002841366,0.004053643,0.003176019,0.1366971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002811129,"about_ca_system_score_gemma":0.003979457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04140645,"about_ca_topic_score_gemma":0.08426706,"domain_scores_codex":[0.9909293,0.00371775,0.0007928805,0.001405868,0.002257141,0.0008970079],"domain_scores_gemma":[0.981082,0.00620904,0.0006829243,0.006047395,0.004585361,0.001393231],"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":[0.000491178,0.0001318037,0.0003588596,0.0003860878,0.00004204352,0.00001382666,0.00002507454,0.0002737585,0.000160164,0.0001238948,0.9923636,0.005629802],"study_design_scores_gemma":[0.006263687,0.00057219,0.01394126,0.0007689745,0.0002912956,0.0002290515,0.0006215932,0.009827819,0.003884684,0.002824224,0.9605709,0.0002043842],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.007754663,0.001123804,0.00233066,0.002601298,0.001248816,0.0009714582,0.9309254,0.03924625,0.01379764],"genre_scores_gemma":[0.005159552,0.0001979581,0.005046037,0.0008979108,0.00007985518,0.0009197773,0.9774699,0.002815865,0.007413023],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.078335,"threshold_uncertainty_score":0.2620567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06929803995441347,"score_gpt":0.3037986320660986,"score_spread":0.2345005921116851,"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."}}