{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:74P4Y7PZNFBVSXMHGLRSKQOHPU","short_pith_number":"pith:74P4Y7PZ","schema_version":"1.0","canonical_sha256":"ff1fcc7df96943595d8732e32541c77d06f76dbe9265fd956927f30fecf1f08b","source":{"kind":"arxiv","id":"2309.07544","version":2},"attestation_state":"computed","paper":{"title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Brucek Khailany, Haoxing Ren, Mingjie Liu, Nathaniel Pinckney","submitted_at":"2023-09-14T09:15:34Z","abstract_excerpt":"The increasing popularity of large language models (LLMs) has paved the way for their application in diverse domains. This paper proposes a benchmarking framework tailored specifically for evaluating LLM performance in the context of Verilog code generation for hardware design and verification. We present a comprehensive evaluation dataset consisting of 156 problems from the Verilog instructional website HDLBits. The evaluation set consists of a diverse set of Verilog code generation tasks, ranging from simple combinational circuits to complex finite state machines. The Verilog code completion"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.07544","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-14T09:15:34Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ead73ea752e161565190d40313b29c806fd6c3fcd8107d09120ee52a9f898c33","abstract_canon_sha256":"7790e01fcbf256c67ff4786202e041df466d86c17319e8f83e16791294ef514f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:23.176572Z","signature_b64":"CTYhd8iyiLEIkHC1SSy/mBhybOz879JbKKAFx8wjFDqsqs36zq7r4TlG4pxialDt0h5H1V+9gMJHujaCNcVKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1fcc7df96943595d8732e32541c77d06f76dbe9265fd956927f30fecf1f08b","last_reissued_at":"2026-07-05T07:22:23.176067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:23.176067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Brucek Khailany, Haoxing Ren, Mingjie Liu, Nathaniel Pinckney","submitted_at":"2023-09-14T09:15:34Z","abstract_excerpt":"The increasing popularity of large language models (LLMs) has paved the way for their application in diverse domains. This paper proposes a benchmarking framework tailored specifically for evaluating LLM performance in the context of Verilog code generation for hardware design and verification. We present a comprehensive evaluation dataset consisting of 156 problems from the Verilog instructional website HDLBits. The evaluation set consists of a diverse set of Verilog code generation tasks, ranging from simple combinational circuits to complex finite state machines. The Verilog code completion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07544","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.07544/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.07544","created_at":"2026-07-05T07:22:23.176127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07544v2","created_at":"2026-07-05T07:22:23.176127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07544","created_at":"2026-07-05T07:22:23.176127+00:00"},{"alias_kind":"pith_short_12","alias_value":"74P4Y7PZNFBV","created_at":"2026-07-05T07:22:23.176127+00:00"},{"alias_kind":"pith_short_16","alias_value":"74P4Y7PZNFBVSXMH","created_at":"2026-07-05T07:22:23.176127+00:00"},{"alias_kind":"pith_short_8","alias_value":"74P4Y7PZ","created_at":"2026-07-05T07:22:23.176127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10285","citing_title":"OpenRTLSet: A Fully Open-Source Dataset for Large Language Model-based Verilog Module Design","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05253","citing_title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28279","citing_title":"Agentic Hardware Design as Repository-Level Code Evolution","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23704","citing_title":"PCB-QA: Evaluating LLMs over the First Printed Circuit Board Design Question-Answer Dataset","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14541","citing_title":"Report for NSF Workshop on AI for Electronic Design Automation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27415","citing_title":"ChipLingo: A Systematic Training Framework for Large Language Models in EDA","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14989","citing_title":"Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU","json":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU.json","graph_json":"https://pith.science/api/pith-number/74P4Y7PZNFBVSXMHGLRSKQOHPU/graph.json","events_json":"https://pith.science/api/pith-number/74P4Y7PZNFBVSXMHGLRSKQOHPU/events.json","paper":"https://pith.science/paper/74P4Y7PZ"},"agent_actions":{"view_html":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU","download_json":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU.json","view_paper":"https://pith.science/paper/74P4Y7PZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07544&json=true","fetch_graph":"https://pith.science/api/pith-number/74P4Y7PZNFBVSXMHGLRSKQOHPU/graph.json","fetch_events":"https://pith.science/api/pith-number/74P4Y7PZNFBVSXMHGLRSKQOHPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU/action/storage_attestation","attest_author":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU/action/author_attestation","sign_citation":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU/action/citation_signature","submit_replication":"https://pith.science/pith/74P4Y7PZNFBVSXMHGLRSKQOHPU/action/replication_record"}},"created_at":"2026-07-05T07:22:23.176127+00:00","updated_at":"2026-07-05T07:22:23.176127+00:00"}