{"id":"W2962725091","doi":"","title":"Structured Generative Models of Natural Source Code","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generative grammar; Source code; Probabilistic logic; Code (set theory); Context (archaeology); Generative model; Natural language processing; Artificial intelligence; Natural language; Rule-based machine translation; Language model; Statistical model; 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":[0.002028039,0.0008506885,0.0005751484,0.001979819,0.0005110956,0.001523286,0.001925492,0.0014761,0.003232596],"category_scores_gemma":[0.01619317,0.0008996109,0.001452646,0.001404859,0.001903762,0.002882224,0.001316102,0.002002678,0.0009999388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00140358,"about_ca_system_score_gemma":0.00142103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006691869,"about_ca_topic_score_gemma":0.01157548,"domain_scores_codex":[0.9984428,0.0006249373,0.00006299357,0.0003967739,0.0003598765,0.0001125557],"domain_scores_gemma":[0.9831366,0.01359344,0.0009715857,0.00117539,0.0009053894,0.0002176512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006589059,0.00007663778,0.004550778,0.0001992129,0.00008364551,0.0003884978,0.0008438428,0.7320086,0.002462044,0.20917,0.004444935,0.04570605],"study_design_scores_gemma":[0.000009641111,0.000009400772,0.0003024798,0.00001999444,0.000009482818,0.0000865344,0.00002555694,0.8869956,0.0004883753,0.1102592,0.001783001,0.0000108721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02641651,0.0003465416,0.968351,0.0005041801,0.0000306639,0.00005951141,0.0008158217,0.001127393,0.002348443],"genre_scores_gemma":[0.6939777,0.0008211731,0.2910915,0.0004271396,0.0001238702,0.0004996026,0.00473984,0.001155614,0.007163697],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006691869,"threshold_uncertainty_score":0.01330584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02337419429426449,"score_gpt":0.2985761800977195,"score_spread":0.275201985803455,"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."}}