{"id":"W4389518884","doi":"10.18653/v1/2023.findings-emnlp.316","title":"The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Code review; Scripting language; Automatic summarization; Code (set theory); Source code; Artificial intelligence; Natural language processing; KPI-driven code analysis; Vault (architecture); Software quality; Software; Programming language; Software development","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":[0.001894022,0.001738532,0.0006853682,0.00523592,0.001560365,0.001812528,0.003034257,0.002560794,0.006998819],"category_scores_gemma":[0.01408812,0.0006138974,0.001501808,0.004054093,0.001100038,0.003041521,0.003548541,0.002927563,0.01010762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001656786,"about_ca_system_score_gemma":0.002683038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01486061,"about_ca_topic_score_gemma":0.03305916,"domain_scores_codex":[0.9967465,0.000635577,0.0003793628,0.0009149804,0.001067198,0.0002562617],"domain_scores_gemma":[0.9930554,0.001990309,0.000627078,0.001859313,0.001891899,0.0005760351],"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":[0.0005915035,0.0005008921,0.01546432,0.001938146,0.0001803844,0.0005127649,0.0008220996,0.008376512,0.006840825,0.006567896,0.8602309,0.09797367],"study_design_scores_gemma":[0.0006013936,0.0003248409,0.02000368,0.0004657055,0.0001173191,0.0008557518,0.0008244107,0.05622695,0.01938707,0.01321068,0.8877091,0.0002731922],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.04796427,0.001838531,0.03648374,0.001588095,0.0006226113,0.0006153811,0.8572398,0.04146068,0.01218703],"genre_scores_gemma":[0.02348125,0.0002166695,0.0325782,0.0003497596,0.00005382012,0.0005656409,0.938578,0.001809153,0.002367634],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01486061,"threshold_uncertainty_score":0.02954823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1370846885467231,"score_gpt":0.3636912366728717,"score_spread":0.2266065481261486,"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."}}