{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GFOSUESMB5NYUQSZOJUUJHFSFJ","short_pith_number":"pith:GFOSUESM","schema_version":"1.0","canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","source":{"kind":"arxiv","id":"2507.13369","version":1},"attestation_state":"computed","paper":{"title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Danyu Lu, Farimah Farahmandi, Kamal Kandula, Mark Tehranipoor, Paul E. Calzada, Sujan Kumar Saha, Tanvir Rahman, Zahin Ibnat","submitted_at":"2025-07-09T17:06:54Z","abstract_excerpt":"Large Language Models (LLMs) are gaining popularity for hardware design automation, particularly through Register Transfer Level (RTL) code generation. In this work, we examine the current literature on RTL generation using LLMs and identify key requirements for training and fine-tuning datasets. We construct a robust Verilog dataset through an automated three-pronged process involving database (DB) creation and management with PostgreSQL, data collection from code hosting sites like OpenCores and GitHub, and data preprocessing to verify the codes' syntax, run logic synthesis, and extract rele"},"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":"2507.13369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-07-09T17:06:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6a0cd547678c8feb85c543171cfb52029838355ee4e0bca55bb21f0d991f8c9","abstract_canon_sha256":"4c00f21155f816d86ceefec792588dab76e10091ec4873f8306a5089565256f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:16.101193Z","signature_b64":"LpNZUeOqdk1AkHIu42gHF7Bya3nnaOmsLPAilGWVc8GhWWYr2ziXkFN+QiK96pQ4CkWv2SLXYNPXh4IyzsoOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315d2a124c0f5b8a42597269449cb22a4152f4174e70c5009f62ae54a86c88b2","last_reissued_at":"2026-07-05T11:39:16.100738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:16.100738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Danyu Lu, Farimah Farahmandi, Kamal Kandula, Mark Tehranipoor, Paul E. Calzada, Sujan Kumar Saha, Tanvir Rahman, Zahin Ibnat","submitted_at":"2025-07-09T17:06:54Z","abstract_excerpt":"Large Language Models (LLMs) are gaining popularity for hardware design automation, particularly through Register Transfer Level (RTL) code generation. In this work, we examine the current literature on RTL generation using LLMs and identify key requirements for training and fine-tuning datasets. We construct a robust Verilog dataset through an automated three-pronged process involving database (DB) creation and management with PostgreSQL, data collection from code hosting sites like OpenCores and GitHub, and data preprocessing to verify the codes' syntax, run logic synthesis, and extract rele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13369","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/2507.13369/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":"2507.13369","created_at":"2026-07-05T11:39:16.100794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13369v1","created_at":"2026-07-05T11:39:16.100794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13369","created_at":"2026-07-05T11:39:16.100794+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFOSUESMB5NY","created_at":"2026-07-05T11:39:16.100794+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFOSUESMB5NYUQSZ","created_at":"2026-07-05T11:39:16.100794+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFOSUESM","created_at":"2026-07-05T11:39:16.100794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15606","citing_title":"Spec2Cov: An Agentic Framework for Code Coverage Closure of Digital Hardware Designs","ref_index":14,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01170","citing_title":"ATLAS: AI-Assisted Threat-to-Assertion Learning for System-on-Chip Security Verification","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15073","citing_title":"Emulation-based System-on-Chip Security Verification: Challenges and Opportunities","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15606","citing_title":"Spec2Cov: An Agentic Framework for Code Coverage Closure of Digital Hardware Designs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21952","citing_title":"Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ","json":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ.json","graph_json":"https://pith.science/api/pith-number/GFOSUESMB5NYUQSZOJUUJHFSFJ/graph.json","events_json":"https://pith.science/api/pith-number/GFOSUESMB5NYUQSZOJUUJHFSFJ/events.json","paper":"https://pith.science/paper/GFOSUESM"},"agent_actions":{"view_html":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ","download_json":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ.json","view_paper":"https://pith.science/paper/GFOSUESM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13369&json=true","fetch_graph":"https://pith.science/api/pith-number/GFOSUESMB5NYUQSZOJUUJHFSFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GFOSUESMB5NYUQSZOJUUJHFSFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/action/storage_attestation","attest_author":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/action/author_attestation","sign_citation":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/action/citation_signature","submit_replication":"https://pith.science/pith/GFOSUESMB5NYUQSZOJUUJHFSFJ/action/replication_record"}},"created_at":"2026-07-05T11:39:16.100794+00:00","updated_at":"2026-07-05T11:39:16.100794+00:00"}