{"id":"W4312943943","doi":"10.1007/978-3-031-21037-2_10","title":"Novice Type Error Diagnosis with Natural Language Models","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Flexibility (engineering); Metric (unit); Constraint (computer-aided design); Natural language; Type (biology); Artificial intelligence; Language model; State (computer science); Data type; Machine learning; Natural language understanding; Natural language processing; Algorithm; Programming language","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":[0.001411189,0.0009862403,0.0005987481,0.001136569,0.0003779815,0.001639109,0.002406989,0.00145321,0.007240238],"category_scores_gemma":[0.01137854,0.0005840718,0.001149443,0.0004560065,0.0007763274,0.003786922,0.00169819,0.002259471,0.003108914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005994661,"about_ca_system_score_gemma":0.001086312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001933644,"about_ca_topic_score_gemma":0.003927511,"domain_scores_codex":[0.9980643,0.000519927,0.0001126046,0.0004431226,0.0007352995,0.0001247847],"domain_scores_gemma":[0.9920409,0.004760431,0.0004122641,0.001655001,0.0009984712,0.0001329227],"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":[0.0004489947,0.0005263388,0.005261777,0.0004919326,0.0000999922,0.001555698,0.0007692752,0.06356062,0.01927861,0.05027021,0.03326194,0.8244746],"study_design_scores_gemma":[0.00005562242,0.0001780473,0.0009500461,0.0001933419,0.0000821391,0.001768064,0.0002438561,0.7669632,0.0478326,0.1537375,0.0279296,0.00006605346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0139426,0.0002487332,0.9667691,0.000468864,0.0000861419,0.00009044683,0.0003260382,0.01034856,0.007719535],"genre_scores_gemma":[0.2523827,0.0003494329,0.7312351,0.0004673216,0.00008644909,0.0001128656,0.001314806,0.001274721,0.01277664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007240238,"threshold_uncertainty_score":0.024221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01822127109074478,"score_gpt":0.2622433089306804,"score_spread":0.2440220378399356,"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."}}