{"id":"W4387869001","doi":"10.1145/3630009","title":"The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Snippet; Artificial intelligence; Code (set theory); Code generation; Machine learning; Artificial neural network; Construct (python library); Set (abstract data type); Programming language; Natural language processing","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":[0.00412961,0.001044217,0.0005683819,0.001317341,0.0005649148,0.001234641,0.00173053,0.00140821,0.001178838],"category_scores_gemma":[0.02177957,0.0003805615,0.0006534695,0.001159107,0.001105854,0.002858296,0.001375159,0.002166109,0.000609077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00155198,"about_ca_system_score_gemma":0.001543544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005671116,"about_ca_topic_score_gemma":0.008019838,"domain_scores_codex":[0.9968021,0.001497934,0.0002436041,0.0005655136,0.000727663,0.0001632078],"domain_scores_gemma":[0.9866261,0.009543783,0.0007659805,0.001482802,0.001318192,0.0002630992],"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":[0.0009613474,0.0005498669,0.01687274,0.001091159,0.0001668452,0.000297874,0.0004746491,0.2627853,0.01005486,0.009590357,0.01529788,0.6818571],"study_design_scores_gemma":[0.0001010409,0.0002597223,0.002651882,0.00009743898,0.00005907144,0.0001261087,0.00009445785,0.969383,0.009819735,0.01332746,0.004042977,0.00003709741],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5322574,0.009701511,0.4262698,0.004227548,0.0004300442,0.0004561643,0.001526988,0.0154771,0.009653416],"genre_scores_gemma":[0.7354818,0.001500948,0.2555051,0.0007565064,0.00008323233,0.0004297448,0.002823895,0.0006267389,0.002792147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005671116,"threshold_uncertainty_score":0.02183968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1099002619407233,"score_gpt":0.3378867384012966,"score_spread":0.2279864764605732,"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."}}