{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GIHXNIXWGEXVP75TF5NBTQEIXT","short_pith_number":"pith:GIHXNIXW","schema_version":"1.0","canonical_sha256":"320f76a2f6312f57ffb32f5a19c088bccc157a4d562aef69bb36a12396ee547e","source":{"kind":"arxiv","id":"2409.11414","version":1},"attestation_state":"computed","paper":{"title":"RTLRewriter: Methodologies for Large Models aided RTL Code Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.AR","authors_text":"Bei Yu, Hong Xu, Lei Chen, Mingxuan Yuan, Ran Chen, Xing Li, Xufeng Yao, Yingzhao Lian, Yiwen Wang","submitted_at":"2024-09-04T09:59:37Z","abstract_excerpt":"Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal progra"},"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":"2409.11414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AR","submitted_at":"2024-09-04T09:59:37Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"f5edc0e8b5700b5ad6d5c5b6776827074ee61694eb9ebb84f6f9f18220348957","abstract_canon_sha256":"e66cb3c6d379b093c45060d247ad09240d5da31e68d2fadaeda4891c6666ddf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:30.455387Z","signature_b64":"Lw47qsRcd8pdNq/+5Z4yLoEdcBMa6ShWtuIOa04mdSVyI98hE+PcEZjAJ5tZ1tabvjyD0h2AHcM0EHYgPgvWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320f76a2f6312f57ffb32f5a19c088bccc157a4d562aef69bb36a12396ee547e","last_reissued_at":"2026-07-05T09:08:30.454922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:30.454922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTLRewriter: Methodologies for Large Models aided RTL Code Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.AR","authors_text":"Bei Yu, Hong Xu, Lei Chen, Mingxuan Yuan, Ran Chen, Xing Li, Xufeng Yao, Yingzhao Lian, Yiwen Wang","submitted_at":"2024-09-04T09:59:37Z","abstract_excerpt":"Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal progra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11414","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/2409.11414/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":"2409.11414","created_at":"2026-07-05T09:08:30.454991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11414v1","created_at":"2026-07-05T09:08:30.454991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11414","created_at":"2026-07-05T09:08:30.454991+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIHXNIXWGEXV","created_at":"2026-07-05T09:08:30.454991+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIHXNIXWGEXVP75T","created_at":"2026-07-05T09:08:30.454991+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIHXNIXW","created_at":"2026-07-05T09:08:30.454991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15537","citing_title":"RTL-BenchMT: Dynamic Maintenance of RTL Generation Benchmark Through Agent-Assisted Analysis and Revision","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04736","citing_title":"ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT","json":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT.json","graph_json":"https://pith.science/api/pith-number/GIHXNIXWGEXVP75TF5NBTQEIXT/graph.json","events_json":"https://pith.science/api/pith-number/GIHXNIXWGEXVP75TF5NBTQEIXT/events.json","paper":"https://pith.science/paper/GIHXNIXW"},"agent_actions":{"view_html":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT","download_json":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT.json","view_paper":"https://pith.science/paper/GIHXNIXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11414&json=true","fetch_graph":"https://pith.science/api/pith-number/GIHXNIXWGEXVP75TF5NBTQEIXT/graph.json","fetch_events":"https://pith.science/api/pith-number/GIHXNIXWGEXVP75TF5NBTQEIXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT/action/storage_attestation","attest_author":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT/action/author_attestation","sign_citation":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT/action/citation_signature","submit_replication":"https://pith.science/pith/GIHXNIXWGEXVP75TF5NBTQEIXT/action/replication_record"}},"created_at":"2026-07-05T09:08:30.454991+00:00","updated_at":"2026-07-05T09:08:30.454991+00:00"}