{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001111225,0.0002813993,0.0002388134,0.0005388416,0.0009927475,0.002366419,0.001828444,0.0001458025,0.00100988],"category_scores_gemma":[0.0005019193,0.0002649293,0.00003704016,0.0006545968,0.0000552549,0.000376442,0.001944822,0.0005024813,0.002467052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002020755,"about_ca_system_score_gemma":0.00001130264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008309698,"about_ca_topic_score_gemma":5.227155e-7,"domain_scores_codex":[0.9974737,0.0003827544,0.0003121461,0.0008032059,0.0006928797,0.0003352687],"domain_scores_gemma":[0.9981278,0.00003980162,0.0002274788,0.0009258381,0.0004790678,0.0002000536],"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":[0.0000187777,0.0001015925,1.293102e-7,0.0001389603,0.00003681191,0.00002004582,0.0001442951,0.0008538084,0.00001062816,0.000283767,0.9844002,0.01399095],"study_design_scores_gemma":[0.0002595743,0.0004998983,0.0000371952,0.0002418959,0.00002869374,0.00006198163,0.00001655044,0.07582864,0.00003588166,0.00008617969,0.9226224,0.0002810808],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0005416605,0.0004435582,0.1005065,0.002227695,0.001322497,0.003384219,0.8767526,0.008946345,0.005874893],"genre_scores_gemma":[0.002964932,0.0002540787,0.006034144,0.0006363583,0.0003403668,8.399377e-7,0.9883102,0.001182602,0.0002765002],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1115575,"threshold_uncertainty_score":0.9999803,"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."}}