{"id":"W4389524428","doi":"10.18653/v1/2023.nlposs-1.25","title":"The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Open source software; Computer science; Code (set theory); Open source; Vault (architecture); Ho chi minh; Natural language processing; Artificial intelligence; Software; Programming language; History; Cartography; Geography; Archaeology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002660235,0.00007015085,0.00006247692,0.00004781909,0.0004533643,0.0002694886,0.000285122,0.00002824365,3.775424e-7],"category_scores_gemma":[0.00009944367,0.00004632385,0.00001287918,0.0001850893,0.00003376192,0.0002966355,0.0002105064,0.00005946396,0.000001748449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003998356,"about_ca_system_score_gemma":0.00002354114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001016081,"about_ca_topic_score_gemma":0.0001299187,"domain_scores_codex":[0.9993607,0.00002134222,0.0001049498,0.0002198791,0.0001054069,0.0001876967],"domain_scores_gemma":[0.9992653,0.0003992532,0.00004101058,0.0002128792,0.00005017512,0.00003134426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003276788,0.00002109271,0.00005876906,0.0001272191,0.00005995674,0.00003346465,0.00305111,0.0002986225,0.1221171,0.5393277,0.1665282,0.168344],"study_design_scores_gemma":[0.0002225365,0.00003899572,0.000006014679,0.00001534511,0.000004680885,0.00001116497,0.0004463904,0.9167155,0.02899447,0.04330418,0.01010847,0.0001322675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00223639,0.000504307,0.9948747,0.001516727,0.0001352194,0.0002191277,0.00007259673,0.0004306197,0.00001031744],"genre_scores_gemma":[0.2218899,0.00009191022,0.7766973,0.0007173214,0.0001063437,0.00003857415,0.0003069948,0.00001184262,0.0001398299],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9164169,"threshold_uncertainty_score":0.3486958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09684993925383269,"score_gpt":0.3615021865434158,"score_spread":0.2646522472895831,"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."}}