{"id":"W3000240292","doi":"10.1145/3344429.3372508","title":"Compiler Error Messages Considered Unhelpful","year":2019,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital","funders":"","keywords":"Computer science; Compiler; Interpreter; Syntax; Syntax error; Process (computing); Programming language; Error detection and correction; Artificial intelligence; Abstract syntax tree; Algorithm","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002347146,0.0000915284,0.0001218516,0.00005529286,0.00008113076,0.0001837983,0.0004644742,0.00004082726,0.0002629095],"category_scores_gemma":[0.00003260524,0.00007464318,0.00004722923,0.0001310208,0.00002204691,0.0002193273,0.0001566283,0.0001987117,0.001520189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001156159,"about_ca_system_score_gemma":0.00002921563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005631031,"about_ca_topic_score_gemma":0.000003764854,"domain_scores_codex":[0.9991297,0.00007439232,0.0001172115,0.0002805531,0.0001659689,0.0002322419],"domain_scores_gemma":[0.9992757,0.0001297374,0.00004380196,0.0004595211,0.00002832033,0.0000629632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007779107,0.0001552345,0.03696177,0.0000459775,0.00007150453,0.00003325,0.0055587,0.00127065,0.001076168,0.2075632,0.02322793,0.7240278],"study_design_scores_gemma":[0.0005802382,0.0001144545,0.01178223,0.00002975175,0.000004107193,0.00002989585,0.0003158045,0.02202184,0.0003699816,0.0006836894,0.9637344,0.0003335743],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1377465,0.0002262562,0.796179,0.008036534,0.001298647,0.0003105165,5.615719e-7,0.002206707,0.05399531],"genre_scores_gemma":[0.87693,6.801352e-7,0.1122537,0.0006599277,0.00001998629,0.000002622759,0.000001158909,0.000006396512,0.0101255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9405065,"threshold_uncertainty_score":0.9992573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01795464734595689,"score_gpt":0.2562612504654603,"score_spread":0.2383066031195034,"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."}}