{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002307766,0.0001492234,0.0001622798,0.0001633689,0.00007981932,0.0001439071,0.001112631,0.00005627021,0.00004729625],"category_scores_gemma":[0.0002323227,0.0001239091,0.00005311905,0.0001174163,0.00004710152,0.0003876913,0.0002349973,0.0005145136,0.000006243808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003717016,"about_ca_system_score_gemma":0.00003536528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006285613,"about_ca_topic_score_gemma":0.00002080755,"domain_scores_codex":[0.9987693,0.0001311344,0.0002127673,0.0003144201,0.0004267809,0.0001455396],"domain_scores_gemma":[0.9991246,0.00009071404,0.0002212343,0.0002121122,0.0003115578,0.00003975939],"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":[0.00002068627,0.00001489644,0.0002298665,0.000006495604,0.00002155068,0.000002049351,0.0005815797,0.007265333,0.0208331,0.8950265,0.00003377699,0.07596417],"study_design_scores_gemma":[0.0001675368,0.00007094799,0.00004758026,0.00004372487,0.000001897355,0.000007918214,0.00001011616,0.8697361,0.01859652,0.1107294,0.0004630183,0.0001252191],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008158857,0.0001475853,0.984733,0.001415031,0.0002585334,0.00006163953,0.000004014442,0.0002899668,0.004931377],"genre_scores_gemma":[0.8198657,0.000006118095,0.1790095,0.0002758902,0.00006049282,0.000004001026,0.00001664918,0.000008563632,0.0007531419],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8624708,"threshold_uncertainty_score":0.5052866,"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."}}