{"id":"W4391681217","doi":"10.1145/3643681","title":"VeriGen: A Large Language Model for Verilog Code Generation","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Design Automation of Electronic Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Army Research Office; National Science Foundation","keywords":"Computer science; Verilog; Correctness; Programming language; Set (abstract data type); Scripting language; Code (set theory); Hardware description language; Compiler; Embedded system; Field-programmable gate array","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":[0.001835361,0.001751873,0.0004812378,0.001161039,0.00035927,0.001353677,0.003533517,0.001238768,0.013219],"category_scores_gemma":[0.01162219,0.001080527,0.001698778,0.0006599127,0.0007661986,0.002691297,0.001562095,0.002556879,0.007100868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001153767,"about_ca_system_score_gemma":0.003156455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004110732,"about_ca_topic_score_gemma":0.008934466,"domain_scores_codex":[0.9984722,0.0004868041,0.0001297933,0.0003402666,0.0004539966,0.0001170168],"domain_scores_gemma":[0.9949809,0.002890165,0.0002505158,0.001133195,0.0006451623,0.000100163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008148248,0.0004145613,0.005738237,0.00199781,0.0001967601,0.0004827327,0.0003032015,0.5134848,0.02077499,0.02578363,0.1136321,0.3163765],"study_design_scores_gemma":[0.0001323093,0.0001339636,0.00030086,0.00009573999,0.0000391655,0.0001469389,0.00002846925,0.9422128,0.01281057,0.01317317,0.03089462,0.0000314323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01829252,0.0007986176,0.8030402,0.0008131145,0.0003483937,0.0005337491,0.007907146,0.162097,0.006169165],"genre_scores_gemma":[0.202864,0.0007809312,0.7361141,0.001091596,0.0001100883,0.001287681,0.02859487,0.02246803,0.006688759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.013219,"threshold_uncertainty_score":0.04422194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04508213604149722,"score_gpt":0.2920347453643743,"score_spread":0.2469526093228771,"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."}}