{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GGVUXYUELNZG2WX6SWYQEUJAVJ","short_pith_number":"pith:GGVUXYUE","schema_version":"1.0","canonical_sha256":"31ab4be2845b726d5afe95b1025120aa594c537f1159619bbba23c8ea28b1544","source":{"kind":"arxiv","id":"2308.00708","version":1},"attestation_state":"computed","paper":{"title":"VeriGen: A Large Language Model for Verilog Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.PL","authors_text":"Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, Hammond Pearce, Ramesh Karri, Shailja Thakur, Siddharth Garg","submitted_at":"2023-07-28T02:57:14Z","abstract_excerpt":"In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by generating high-quality Verilog code, a common language for designing and modeling digital systems. We fine-tune pre-existing LLMs on Verilog datasets compiled from GitHub and Verilog textbooks. We evaluate the functional correctness of the generated Verilog code using a specially designed test suite, featuring a custom problem set and testing benches. Here, our fine-tuned open-source CodeGen-16B model outperforms the commercial state-of-the-art GPT-3.5-turbo model with a 1.1% overall increa"},"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":"2308.00708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.PL","submitted_at":"2023-07-28T02:57:14Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"880f57f48339b1e7148bf4ed368021b2b590ec375c9f713d9b68509332f44e49","abstract_canon_sha256":"5adc54bef83caf9cd46d6d7de830819fce908c53cc436005955cb59240dfa7d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:56.123496Z","signature_b64":"K1rlvmcKrsfMgwxhe3AD4f/eOcjgxQ6A/eghct+jXJkB54JMji5a6atWlhyQP2MEn4tIEzE6FGWIXcPV4uoPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ab4be2845b726d5afe95b1025120aa594c537f1159619bbba23c8ea28b1544","last_reissued_at":"2026-07-05T06:36:56.122909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:56.122909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VeriGen: A Large Language Model for Verilog Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.PL","authors_text":"Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, Hammond Pearce, Ramesh Karri, Shailja Thakur, Siddharth Garg","submitted_at":"2023-07-28T02:57:14Z","abstract_excerpt":"In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by generating high-quality Verilog code, a common language for designing and modeling digital systems. We fine-tune pre-existing LLMs on Verilog datasets compiled from GitHub and Verilog textbooks. We evaluate the functional correctness of the generated Verilog code using a specially designed test suite, featuring a custom problem set and testing benches. Here, our fine-tuned open-source CodeGen-16B model outperforms the commercial state-of-the-art GPT-3.5-turbo model with a 1.1% overall increa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00708","kind":"arxiv","version":1},"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/2308.00708/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":"2308.00708","created_at":"2026-07-05T06:36:56.122983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.00708v1","created_at":"2026-07-05T06:36:56.122983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00708","created_at":"2026-07-05T06:36:56.122983+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGVUXYUELNZG","created_at":"2026-07-05T06:36:56.122983+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGVUXYUELNZG2WX6","created_at":"2026-07-05T06:36:56.122983+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGVUXYUE","created_at":"2026-07-05T06:36:56.122983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28279","citing_title":"Agentic Hardware Design as Repository-Level Code Evolution","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19959","citing_title":"From Concept to Practice: an Automated LLM-aided UVM Machine for RTL Verification","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03053","citing_title":"Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08715","citing_title":"VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03144","citing_title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23100","citing_title":"From Language to Logic: Bridging LLMs & Formal Representations for RTL Assertion Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19856","citing_title":"ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05983","citing_title":"Arch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware Design","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ","json":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ.json","graph_json":"https://pith.science/api/pith-number/GGVUXYUELNZG2WX6SWYQEUJAVJ/graph.json","events_json":"https://pith.science/api/pith-number/GGVUXYUELNZG2WX6SWYQEUJAVJ/events.json","paper":"https://pith.science/paper/GGVUXYUE"},"agent_actions":{"view_html":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ","download_json":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ.json","view_paper":"https://pith.science/paper/GGVUXYUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.00708&json=true","fetch_graph":"https://pith.science/api/pith-number/GGVUXYUELNZG2WX6SWYQEUJAVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GGVUXYUELNZG2WX6SWYQEUJAVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ/action/storage_attestation","attest_author":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ/action/author_attestation","sign_citation":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ/action/citation_signature","submit_replication":"https://pith.science/pith/GGVUXYUELNZG2WX6SWYQEUJAVJ/action/replication_record"}},"created_at":"2026-07-05T06:36:56.122983+00:00","updated_at":"2026-07-05T06:36:56.122983+00:00"}