{"id":"W2060384944","doi":"10.1145/2597073.2597102","title":"Syntax errors just aren't natural: improving error reporting with language models","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Syntax error; Abstract syntax tree; Programming language; Syntax; Source code; Compiler; Java; Abstract syntax; Parsing; Consistency (knowledge bases); Exploit; Natural language processing; Artificial intelligence","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":[0.01757523,0.001873406,0.001312365,0.002991234,0.0009729753,0.004673979,0.003371477,0.002147369,0.001606796],"category_scores_gemma":[0.1060279,0.001669256,0.00204746,0.002245454,0.001909604,0.01396365,0.004054405,0.003683462,0.001405139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001688271,"about_ca_system_score_gemma":0.003948457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007551503,"about_ca_topic_score_gemma":0.0108982,"domain_scores_codex":[0.9840552,0.008602047,0.001285334,0.00282468,0.002807854,0.0004247958],"domain_scores_gemma":[0.9015555,0.06695445,0.008828943,0.01427954,0.007608086,0.0007734409],"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":[0.001113698,0.001118675,0.04773587,0.001071872,0.0004967263,0.0008896648,0.006126192,0.3599703,0.02037512,0.05405834,0.01268315,0.4943604],"study_design_scores_gemma":[0.00003707392,0.0000893417,0.0009395421,0.00007638777,0.0000616815,0.0001142252,0.0002384798,0.957206,0.006528794,0.03163817,0.002999956,0.00007033944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03354607,0.000167402,0.9471316,0.0007855219,0.00005636589,0.0001651653,0.0005439603,0.0167477,0.0008562036],"genre_scores_gemma":[0.267129,0.0002311264,0.7275997,0.0003686207,0.0000575212,0.0002674787,0.001305801,0.002222427,0.0008183762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01757523,"threshold_uncertainty_score":0.09294784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02666657826189673,"score_gpt":0.2828682662558349,"score_spread":0.2562016879939382,"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."}}