{"id":"W4385573986","doi":"10.18653/v1/2022.findings-emnlp.174","title":"CodeExp: Explanatory Code Document Generation","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Code (set theory); Task (project management); Baseline (sea); Code generation; Source code; Software; Source lines of code; Machine learning; Scale (ratio); Data mining; Artificial intelligence; Information retrieval; Programming language; Key (lock); Set (abstract data type)","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":[0.001491632,0.001540327,0.0003949986,0.001397775,0.0003398563,0.001188935,0.002144352,0.001297386,0.009976814],"category_scores_gemma":[0.01133908,0.0005038996,0.0009405275,0.0009138711,0.0004264163,0.002009033,0.001564074,0.00173644,0.005959145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007907682,"about_ca_system_score_gemma":0.001386943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004775415,"about_ca_topic_score_gemma":0.01003902,"domain_scores_codex":[0.998943,0.0003380039,0.00007238695,0.0003306393,0.0002518086,0.00006406606],"domain_scores_gemma":[0.9945565,0.002846582,0.0002615154,0.001278928,0.0009071279,0.0001493192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005463614,0.000467354,0.01160233,0.001490119,0.0001312481,0.0005072963,0.0007509683,0.04726824,0.01170179,0.0110313,0.3510945,0.5634085],"study_design_scores_gemma":[0.0002504519,0.0002854555,0.005663207,0.0002551007,0.00007514431,0.0005630279,0.0003077395,0.7564,0.03808056,0.01990276,0.1781038,0.0001127711],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06838025,0.001291472,0.5766854,0.00193707,0.0006668757,0.001269875,0.04551535,0.2884547,0.0157991],"genre_scores_gemma":[0.2286224,0.0006640368,0.6062029,0.001025579,0.000110221,0.001328149,0.1373988,0.009943427,0.01470454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009976814,"threshold_uncertainty_score":0.03337574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02828526137936499,"score_gpt":0.2698888864403468,"score_spread":0.2416036250609818,"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."}}