{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CB72BBBGPVC3BXSFHJ7DGXVV7P","short_pith_number":"pith:CB72BBBG","schema_version":"1.0","canonical_sha256":"107fa084267d45b0de453a7e335eb5fbe9f3d03741b977b0bbca49115566b762","source":{"kind":"arxiv","id":"2407.16237","version":2},"attestation_state":"computed","paper":{"title":"OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Chenyang Yin, Dahua Lin, Demin Song, Fan Cui, Guangyu Sun, Kexing Zhou, Qiang Xu, Qipeng Guo, Xingcheng Zhang, Youwei Xiao, Yun (Eric) Liang","submitted_at":"2024-07-23T07:22:25Z","abstract_excerpt":"Recent studies have demonstrated the significant potential of Large Language Models (LLMs) in generating Register Transfer Level (RTL) code, with notable advancements showcased by commercial models such as GPT-4 and Claude3-Opus. However, these proprietary LLMs often raise concerns regarding privacy and security. While open-source LLMs offer solutions to these concerns, they typically underperform commercial models in RTL code generation tasks, primarily due to the scarcity of high-quality open-source RTL datasets. To address this challenge, we introduce OriGen , a fully open-source framework "},"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":"2407.16237","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2024-07-23T07:22:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dec653c47c693e44f50ab4f9dd8f40a4668f784fe3836f5286a201ab0355643c","abstract_canon_sha256":"98e276da16d7a75e6b0ac37c0d63eadce49980b80cac0d7ff1d95f9d6122ae10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:36.625269Z","signature_b64":"vPohVc4KcjWlh7jbmhq2nW24tom20CeWFntTUiaxzT3yZgimnLqYsCLCFQDqpWcXTj1DJS0JIU4yPgJ9EfHICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107fa084267d45b0de453a7e335eb5fbe9f3d03741b977b0bbca49115566b762","last_reissued_at":"2026-07-05T09:01:36.624745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:36.624745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Chenyang Yin, Dahua Lin, Demin Song, Fan Cui, Guangyu Sun, Kexing Zhou, Qiang Xu, Qipeng Guo, Xingcheng Zhang, Youwei Xiao, Yun (Eric) Liang","submitted_at":"2024-07-23T07:22:25Z","abstract_excerpt":"Recent studies have demonstrated the significant potential of Large Language Models (LLMs) in generating Register Transfer Level (RTL) code, with notable advancements showcased by commercial models such as GPT-4 and Claude3-Opus. However, these proprietary LLMs often raise concerns regarding privacy and security. While open-source LLMs offer solutions to these concerns, they typically underperform commercial models in RTL code generation tasks, primarily due to the scarcity of high-quality open-source RTL datasets. To address this challenge, we introduce OriGen , a fully open-source framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16237","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/2407.16237/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":"2407.16237","created_at":"2026-07-05T09:01:36.624798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16237v2","created_at":"2026-07-05T09:01:36.624798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16237","created_at":"2026-07-05T09:01:36.624798+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB72BBBGPVC3","created_at":"2026-07-05T09:01:36.624798+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB72BBBGPVC3BXSF","created_at":"2026-07-05T09:01:36.624798+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB72BBBG","created_at":"2026-07-05T09:01:36.624798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08976","citing_title":"RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07925","citing_title":"ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28279","citing_title":"Agentic Hardware Design as Repository-Level Code Evolution","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26498","citing_title":"Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15537","citing_title":"RTL-BenchMT: Dynamic Maintenance of RTL Generation Benchmark Through Agent-Assisted Analysis and Revision","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23602","citing_title":"TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18162","citing_title":"VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P","json":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P.json","graph_json":"https://pith.science/api/pith-number/CB72BBBGPVC3BXSFHJ7DGXVV7P/graph.json","events_json":"https://pith.science/api/pith-number/CB72BBBGPVC3BXSFHJ7DGXVV7P/events.json","paper":"https://pith.science/paper/CB72BBBG"},"agent_actions":{"view_html":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P","download_json":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P.json","view_paper":"https://pith.science/paper/CB72BBBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16237&json=true","fetch_graph":"https://pith.science/api/pith-number/CB72BBBGPVC3BXSFHJ7DGXVV7P/graph.json","fetch_events":"https://pith.science/api/pith-number/CB72BBBGPVC3BXSFHJ7DGXVV7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P/action/storage_attestation","attest_author":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P/action/author_attestation","sign_citation":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P/action/citation_signature","submit_replication":"https://pith.science/pith/CB72BBBGPVC3BXSFHJ7DGXVV7P/action/replication_record"}},"created_at":"2026-07-05T09:01:36.624798+00:00","updated_at":"2026-07-05T09:01:36.624798+00:00"}