{"id":"W4288281409","doi":"10.48550/arxiv.1907.07803","title":"Syntax and Stack Overflow: A methodology for extracting a corpus of\\n syntax errors and fixes","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Syntax error; Computer science; Python (programming language); Syntax; Abstract syntax tree; Parsing; Programming language; Abstract syntax; Source code; Natural language processing; Artificial intelligence","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":[0.008007989,0.00228474,0.001052012,0.02130881,0.002364645,0.003356652,0.002857231,0.002668429,0.008875805],"category_scores_gemma":[0.04307223,0.001259962,0.002080116,0.01440637,0.002506756,0.006334919,0.007834288,0.003354536,0.0123014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002373378,"about_ca_system_score_gemma":0.007340484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01492012,"about_ca_topic_score_gemma":0.02821362,"domain_scores_codex":[0.985182,0.002400409,0.003700536,0.003959078,0.004098472,0.0006594274],"domain_scores_gemma":[0.9641188,0.01356193,0.005459573,0.008209655,0.007831549,0.0008183516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005742533,0.0005089147,0.05941997,0.008846986,0.0003925285,0.002203548,0.01569638,0.00413045,0.02733812,0.02033792,0.5186789,0.3418721],"study_design_scores_gemma":[0.0001634247,0.0001951221,0.09967879,0.001070541,0.0002018642,0.001691092,0.005060408,0.01917468,0.02845561,0.01846845,0.8254012,0.000438766],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.09765211,0.001723146,0.1666307,0.001648098,0.0007173632,0.003716281,0.6584808,0.04973324,0.01969827],"genre_scores_gemma":[0.05135258,0.0005444523,0.295034,0.0006266602,0.0001535495,0.006139663,0.6329473,0.005921577,0.007280156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02130881,"threshold_uncertainty_score":0.04235077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1771833311109095,"score_gpt":0.2577906096931637,"score_spread":0.08060727858225417,"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."}}