{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3HS7B7BTNNVXUOC53LWPHNJAMR","short_pith_number":"pith:3HS7B7BT","schema_version":"1.0","canonical_sha256":"d9e5f0fc336b6b7a385ddaecf3b52064587d532802d6116090effb19cc55adbc","source":{"kind":"arxiv","id":"2312.08617","version":5},"attestation_state":"computed","paper":{"title":"RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.PL","authors_text":"Hongce Zhang, Qijun Zhang, Shang Liu, Wenji Fang, Yao Lu, Zhiyao Xie","submitted_at":"2023-12-14T02:42:15Z","abstract_excerpt":"The automatic generation of RTL code (e.g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently. However, most existing approaches heavily rely on commercial LLMs such as ChatGPT, while open-source LLMs tailored for this specific design generation task exhibit notably inferior performance. The absence of high-quality open-source solutions restricts the flexibility and data privacy of this emerging technique. In this study, we present a new customized LLM solution with a modest parameter count of only 7B, achieving b"},"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":"2312.08617","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.PL","submitted_at":"2023-12-14T02:42:15Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"11163b8de5a119840d3499607521b844e81ed614e5817c9552e4350b7d14d9ea","abstract_canon_sha256":"b93d0dea1f3c62d8de385ad864db1c127a268f617573ee152d24e5372945d9af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:02.543266Z","signature_b64":"RBUXs1LZuhnVGzC17QB5T/V4FIbUqgbVx9YLtSBX0hA8rfNrUNCo2zKlNOGMDAYNiqTkHJJwm4Lh0oaIj2GICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9e5f0fc336b6b7a385ddaecf3b52064587d532802d6116090effb19cc55adbc","last_reissued_at":"2026-07-05T11:49:02.542800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:02.542800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.PL","authors_text":"Hongce Zhang, Qijun Zhang, Shang Liu, Wenji Fang, Yao Lu, Zhiyao Xie","submitted_at":"2023-12-14T02:42:15Z","abstract_excerpt":"The automatic generation of RTL code (e.g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently. However, most existing approaches heavily rely on commercial LLMs such as ChatGPT, while open-source LLMs tailored for this specific design generation task exhibit notably inferior performance. The absence of high-quality open-source solutions restricts the flexibility and data privacy of this emerging technique. In this study, we present a new customized LLM solution with a modest parameter count of only 7B, achieving b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08617","kind":"arxiv","version":5},"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/2312.08617/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":"2312.08617","created_at":"2026-07-05T11:49:02.542855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08617v5","created_at":"2026-07-05T11:49:02.542855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08617","created_at":"2026-07-05T11:49:02.542855+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HS7B7BTNNVX","created_at":"2026-07-05T11:49:02.542855+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HS7B7BTNNVXUOC5","created_at":"2026-07-05T11:49:02.542855+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HS7B7BT","created_at":"2026-07-05T11:49:02.542855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05253","citing_title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28279","citing_title":"Agentic Hardware Design as Repository-Level Code Evolution","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26498","citing_title":"Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24218","citing_title":"RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19856","citing_title":"ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR","json":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR.json","graph_json":"https://pith.science/api/pith-number/3HS7B7BTNNVXUOC53LWPHNJAMR/graph.json","events_json":"https://pith.science/api/pith-number/3HS7B7BTNNVXUOC53LWPHNJAMR/events.json","paper":"https://pith.science/paper/3HS7B7BT"},"agent_actions":{"view_html":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR","download_json":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR.json","view_paper":"https://pith.science/paper/3HS7B7BT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08617&json=true","fetch_graph":"https://pith.science/api/pith-number/3HS7B7BTNNVXUOC53LWPHNJAMR/graph.json","fetch_events":"https://pith.science/api/pith-number/3HS7B7BTNNVXUOC53LWPHNJAMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR/action/storage_attestation","attest_author":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR/action/author_attestation","sign_citation":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR/action/citation_signature","submit_replication":"https://pith.science/pith/3HS7B7BTNNVXUOC53LWPHNJAMR/action/replication_record"}},"created_at":"2026-07-05T11:49:02.542855+00:00","updated_at":"2026-07-05T11:49:02.542855+00:00"}