{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5HPBAFXDXDUO6NUFHXUEVZDOWX","short_pith_number":"pith:5HPBAFXD","schema_version":"1.0","canonical_sha256":"e9de1016e3b8e8ef36853de84ae46eb5e485440b886746e1f4bf2f635c66323e","source":{"kind":"arxiv","id":"2407.18333","version":1},"attestation_state":"computed","paper":{"title":"AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Chao Li, Jieru Zhao, Mingzhe Gao, Minyi Guo, Wenchao Ding, Xiaofeng Hou, Yu Feng, Zhe Lin","submitted_at":"2024-07-21T16:42:45Z","abstract_excerpt":"Recently, the use of large language models (LLMs) for software code generation, e.g., C/C++ and Python, has proven a great success. However, LLMs still suffer from low syntactic and functional correctness when it comes to the generation of register-transfer level (RTL) code, such as Verilog. To address this issue, in this paper, we develop AutoVCoder, a systematic open-source framework that significantly improves the LLMs' correctness of generating Verilog code and enhances the quality of its output at the same time. Our framework integrates three novel techniques, including a high-quality har"},"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":"2407.18333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-07-21T16:42:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5e2c247b72525afd0f732a8369fab8b451b6a28b8d5e4575beac885abbd231fa","abstract_canon_sha256":"b9677b2c52ec4ae2d25c2eb81e95b6ed902dac7988cf56ab14b73ae5812bfcb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:48.016856Z","signature_b64":"M+VHBKqAPKwWcOpc8QuKS+8ASwbqmcQ0OywGSc/bk8GbRbH/Asy6VVneApJHlOOwwcX8D+V8V30fAS0lgbP8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9de1016e3b8e8ef36853de84ae46eb5e485440b886746e1f4bf2f635c66323e","last_reissued_at":"2026-07-05T08:48:48.016094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:48.016094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Chao Li, Jieru Zhao, Mingzhe Gao, Minyi Guo, Wenchao Ding, Xiaofeng Hou, Yu Feng, Zhe Lin","submitted_at":"2024-07-21T16:42:45Z","abstract_excerpt":"Recently, the use of large language models (LLMs) for software code generation, e.g., C/C++ and Python, has proven a great success. However, LLMs still suffer from low syntactic and functional correctness when it comes to the generation of register-transfer level (RTL) code, such as Verilog. To address this issue, in this paper, we develop AutoVCoder, a systematic open-source framework that significantly improves the LLMs' correctness of generating Verilog code and enhances the quality of its output at the same time. Our framework integrates three novel techniques, including a high-quality har"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18333","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/2407.18333/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":"2407.18333","created_at":"2026-07-05T08:48:48.016358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18333v1","created_at":"2026-07-05T08:48:48.016358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18333","created_at":"2026-07-05T08:48:48.016358+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HPBAFXDXDUO","created_at":"2026-07-05T08:48:48.016358+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HPBAFXDXDUO6NUF","created_at":"2026-07-05T08:48:48.016358+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HPBAFXD","created_at":"2026-07-05T08:48:48.016358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26498","citing_title":"Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation","ref_index":12,"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":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX","json":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX.json","graph_json":"https://pith.science/api/pith-number/5HPBAFXDXDUO6NUFHXUEVZDOWX/graph.json","events_json":"https://pith.science/api/pith-number/5HPBAFXDXDUO6NUFHXUEVZDOWX/events.json","paper":"https://pith.science/paper/5HPBAFXD"},"agent_actions":{"view_html":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX","download_json":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX.json","view_paper":"https://pith.science/paper/5HPBAFXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18333&json=true","fetch_graph":"https://pith.science/api/pith-number/5HPBAFXDXDUO6NUFHXUEVZDOWX/graph.json","fetch_events":"https://pith.science/api/pith-number/5HPBAFXDXDUO6NUFHXUEVZDOWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX/action/storage_attestation","attest_author":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX/action/author_attestation","sign_citation":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX/action/citation_signature","submit_replication":"https://pith.science/pith/5HPBAFXDXDUO6NUFHXUEVZDOWX/action/replication_record"}},"created_at":"2026-07-05T08:48:48.016358+00:00","updated_at":"2026-07-05T08:48:48.016358+00:00"}