{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6QPMTHOXDMA2ANK3D2V3SBF3VE","short_pith_number":"pith:6QPMTHOX","schema_version":"1.0","canonical_sha256":"f41ec99dd71b01a0355b1eabb904bba93253679e0ff73a585db0aab407a7537e","source":{"kind":"arxiv","id":"2402.03289","version":1},"attestation_state":"computed","paper":{"title":"Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.LG","authors_text":"Animesh Basak Chowdhury, Jeyavijayan Rajendran, Matthew DeLorenzo, Ramesh Karri, Shailja Thakur, Siddharth Garg, Vasudev Gohil","submitted_at":"2024-02-05T18:47:04Z","abstract_excerpt":"Existing large language models (LLMs) for register transfer level code generation face challenges like compilation failures and suboptimal power, performance, and area (PPA) efficiency. This is due to the lack of PPA awareness in conventional transformer decoding algorithms. In response, we present an automated transformer decoding algorithm that integrates Monte Carlo tree-search for lookahead, guiding the transformer to produce compilable, functionally correct, and PPA-optimized code. Empirical evaluation with a fine-tuned language model on RTL codesets shows that our proposed technique cons"},"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":"2402.03289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T18:47:04Z","cross_cats_sorted":["cs.AI","cs.AR"],"title_canon_sha256":"1f80aac536f2ff169a7a2722e2afd4afd4cbdf2a382bbbde2eb4a99255c0c742","abstract_canon_sha256":"ad503cbc902ff2c8d3db70536048613bb5c6dfdff0fa8bf542e2c72c5d339719"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:33.539311Z","signature_b64":"ZZuoGqyORqHE1qXBGs558jqMg2oP9wgIVSvCNTbKrzTn2y4YvkhxTU2xfA2rBTWyBTb/iTbWfYHWCQDFCJZPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f41ec99dd71b01a0355b1eabb904bba93253679e0ff73a585db0aab407a7537e","last_reissued_at":"2026-07-05T07:41:33.538908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:33.538908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.LG","authors_text":"Animesh Basak Chowdhury, Jeyavijayan Rajendran, Matthew DeLorenzo, Ramesh Karri, Shailja Thakur, Siddharth Garg, Vasudev Gohil","submitted_at":"2024-02-05T18:47:04Z","abstract_excerpt":"Existing large language models (LLMs) for register transfer level code generation face challenges like compilation failures and suboptimal power, performance, and area (PPA) efficiency. This is due to the lack of PPA awareness in conventional transformer decoding algorithms. In response, we present an automated transformer decoding algorithm that integrates Monte Carlo tree-search for lookahead, guiding the transformer to produce compilable, functionally correct, and PPA-optimized code. Empirical evaluation with a fine-tuned language model on RTL codesets shows that our proposed technique cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03289","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/2402.03289/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":"2402.03289","created_at":"2026-07-05T07:41:33.538964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03289v1","created_at":"2026-07-05T07:41:33.538964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03289","created_at":"2026-07-05T07:41:33.538964+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QPMTHOXDMA2","created_at":"2026-07-05T07:41:33.538964+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QPMTHOXDMA2ANK3","created_at":"2026-07-05T07:41:33.538964+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QPMTHOX","created_at":"2026-07-05T07:41:33.538964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06530","citing_title":"RTLScout: Joint Agentic Code and Synthesis Optimization for Efficient Digital Circuits","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":12,"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":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04736","citing_title":"ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14989","citing_title":"Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02431","citing_title":"ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE","json":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE.json","graph_json":"https://pith.science/api/pith-number/6QPMTHOXDMA2ANK3D2V3SBF3VE/graph.json","events_json":"https://pith.science/api/pith-number/6QPMTHOXDMA2ANK3D2V3SBF3VE/events.json","paper":"https://pith.science/paper/6QPMTHOX"},"agent_actions":{"view_html":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE","download_json":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE.json","view_paper":"https://pith.science/paper/6QPMTHOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03289&json=true","fetch_graph":"https://pith.science/api/pith-number/6QPMTHOXDMA2ANK3D2V3SBF3VE/graph.json","fetch_events":"https://pith.science/api/pith-number/6QPMTHOXDMA2ANK3D2V3SBF3VE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE/action/storage_attestation","attest_author":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE/action/author_attestation","sign_citation":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE/action/citation_signature","submit_replication":"https://pith.science/pith/6QPMTHOXDMA2ANK3D2V3SBF3VE/action/replication_record"}},"created_at":"2026-07-05T07:41:33.538964+00:00","updated_at":"2026-07-05T07:41:33.538964+00:00"}