{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NV4TOA5SZ72WVL4PRIC3B4YO4U","short_pith_number":"pith:NV4TOA5S","schema_version":"1.0","canonical_sha256":"6d793703b2cff56aaf8f8a05b0f30ee503bc751fc5dc8da9ba993d66bc1fbe59","source":{"kind":"arxiv","id":"2402.03375","version":3},"attestation_state":"computed","paper":{"title":"BetterV: Controlled Verilog Generation with Discriminative Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.AI","authors_text":"Bei Yu, Hui-Ling Zhen, Mingxuan Yuan, Yu Huang, Zehua Pei","submitted_at":"2024-02-03T08:00:12Z","abstract_excerpt":"Due to the growing complexity of modern Integrated Circuits (ICs), there is a need for automated circuit design methods. Recent years have seen rising research in hardware design language generation to facilitate the design process. In this work, we propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific datasets and incorporates generative discriminators for guidance on particular design demands. The Verilog modules are collected, filtered and processed from internet to form a clean and abundant dataset. Instruct-tuning m"},"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":"2402.03375","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-03T08:00:12Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"2dd0ddd201ac7e59228eb414732f867a60ca1a13436f81d1eb93a559871be329","abstract_canon_sha256":"d405c06e6060081ce777ca3c79fc4f77879f0f404f44676e569e52618772be8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:21.756175Z","signature_b64":"WRGAPM5LE4efjwUzcViLSAj0HuJnMiq8WZGuSMVjFxDrjs6aN7DIXlTcbLBTPfRhfX9C3pIRAYGO08IbdPBdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d793703b2cff56aaf8f8a05b0f30ee503bc751fc5dc8da9ba993d66bc1fbe59","last_reissued_at":"2026-07-05T08:14:21.755585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:21.755585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BetterV: Controlled Verilog Generation with Discriminative Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.AI","authors_text":"Bei Yu, Hui-Ling Zhen, Mingxuan Yuan, Yu Huang, Zehua Pei","submitted_at":"2024-02-03T08:00:12Z","abstract_excerpt":"Due to the growing complexity of modern Integrated Circuits (ICs), there is a need for automated circuit design methods. Recent years have seen rising research in hardware design language generation to facilitate the design process. In this work, we propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific datasets and incorporates generative discriminators for guidance on particular design demands. The Verilog modules are collected, filtered and processed from internet to form a clean and abundant dataset. Instruct-tuning m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03375","kind":"arxiv","version":3},"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/2402.03375/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":"2402.03375","created_at":"2026-07-05T08:14:21.755668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03375v3","created_at":"2026-07-05T08:14:21.755668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03375","created_at":"2026-07-05T08:14:21.755668+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV4TOA5SZ72W","created_at":"2026-07-05T08:14:21.755668+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV4TOA5SZ72WVL4P","created_at":"2026-07-05T08:14:21.755668+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV4TOA5S","created_at":"2026-07-05T08:14:21.755668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08976","citing_title":"RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models","ref_index":27,"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":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05253","citing_title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26498","citing_title":"Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation","ref_index":3,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18162","citing_title":"VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18445","citing_title":"AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14989","citing_title":"Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15001","citing_title":"COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U","json":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U.json","graph_json":"https://pith.science/api/pith-number/NV4TOA5SZ72WVL4PRIC3B4YO4U/graph.json","events_json":"https://pith.science/api/pith-number/NV4TOA5SZ72WVL4PRIC3B4YO4U/events.json","paper":"https://pith.science/paper/NV4TOA5S"},"agent_actions":{"view_html":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U","download_json":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U.json","view_paper":"https://pith.science/paper/NV4TOA5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03375&json=true","fetch_graph":"https://pith.science/api/pith-number/NV4TOA5SZ72WVL4PRIC3B4YO4U/graph.json","fetch_events":"https://pith.science/api/pith-number/NV4TOA5SZ72WVL4PRIC3B4YO4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U/action/storage_attestation","attest_author":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U/action/author_attestation","sign_citation":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U/action/citation_signature","submit_replication":"https://pith.science/pith/NV4TOA5SZ72WVL4PRIC3B4YO4U/action/replication_record"}},"created_at":"2026-07-05T08:14:21.755668+00:00","updated_at":"2026-07-05T08:14:21.755668+00:00"}