{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000393105,0.0001144365,0.0001318515,0.0001438148,0.00008665783,0.0001400043,0.0002317506,0.00004504227,0.000008677729],"category_scores_gemma":[0.0003426096,0.0001021205,0.00001561015,0.0003225033,0.00006786802,0.0002739224,0.0005016871,0.00009413096,0.00001552871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004678815,"about_ca_system_score_gemma":0.00003546181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006498321,"about_ca_topic_score_gemma":0.0001587276,"domain_scores_codex":[0.9989089,0.00003884465,0.0001050724,0.0004333045,0.0002131987,0.0003007112],"domain_scores_gemma":[0.9988844,0.0003691588,0.00001301825,0.0004742665,0.00006735857,0.0001918428],"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":[0.00009307343,0.00005989815,0.01606819,0.0002853418,0.0001423062,0.0004032616,0.0295184,0.009013269,0.1599066,0.003020446,0.001069637,0.7804196],"study_design_scores_gemma":[0.000153017,0.0001711849,0.003012711,0.00004594902,0.000004819482,0.000184168,0.0001450138,0.9628552,0.03223012,0.0008757141,0.00004489564,0.0002772448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5073207,0.00005304148,0.4921708,0.00005290724,0.00008356888,0.00009183797,7.149019e-7,0.0001501562,0.00007630903],"genre_scores_gemma":[0.8118752,0.000001864608,0.1878972,0.0001022005,0.00003756929,0.000002255617,8.792396e-8,0.000009746113,0.00007387428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9538419,"threshold_uncertainty_score":0.4164355,"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."}}