{"id":"W2795753518","doi":"10.1109/saner.2018.8330219","title":"Syntax and sensibility: Using language models to detect and correct syntax errors","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Nvidia","keywords":"Computer science; Syntax error; Syntax; Programming language; Parsing; Natural language processing; Java; Abstract syntax; Abstract syntax tree; Artificial intelligence; Language model; Source code; Security token; Code (set theory)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003735905,0.002823132,0.0008793137,0.002499811,0.0005075504,0.002518144,0.002372957,0.002068344,0.004002538],"category_scores_gemma":[0.0283967,0.0009937031,0.001434323,0.001022439,0.001195128,0.007248777,0.002419654,0.00303669,0.003584369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025512,"about_ca_system_score_gemma":0.002208047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006621036,"about_ca_topic_score_gemma":0.008812121,"domain_scores_codex":[0.9969398,0.00128521,0.0002142853,0.0009285629,0.0004557708,0.000176376],"domain_scores_gemma":[0.9880938,0.007047667,0.001173675,0.00186932,0.001509609,0.0003059712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008891474,0.0004830768,0.02985647,0.001101068,0.0004040132,0.000934588,0.002692241,0.08795638,0.04403979,0.004267092,0.02043854,0.8069376],"study_design_scores_gemma":[0.0001159383,0.0004827396,0.008162111,0.0002798381,0.0002660881,0.0006835492,0.000752332,0.9142117,0.04003159,0.02298728,0.01181421,0.0002126129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1561944,0.00117533,0.7470572,0.00194759,0.0005286307,0.0003799763,0.002883962,0.08408834,0.005744453],"genre_scores_gemma":[0.5621796,0.0004803606,0.4238623,0.0008803104,0.0001103001,0.0002123359,0.003750717,0.003602352,0.004921602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006621036,"threshold_uncertainty_score":0.01975757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03567084205301174,"score_gpt":0.2922250463662905,"score_spread":0.2565542043132788,"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."}}