{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YS6CDKRMNT72ZVZCA3GGLXFDU3","short_pith_number":"pith:YS6CDKRM","schema_version":"1.0","canonical_sha256":"c4bc21aa2c6cffacd72206cc65dca3a6c53ff26f168a94b5498975ab8c34a945","source":{"kind":"arxiv","id":"2504.08862","version":1},"attestation_state":"computed","paper":{"title":"RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Junliang Lv, Nan Guo, Peiyang Wu, Xiaochun Ye, Xiao Xiao","submitted_at":"2025-04-11T09:04:50Z","abstract_excerpt":"As an essential part of modern hardware design, manually writing Register Transfer Level (RTL) code such as Verilog is often labor-intensive. Following the tremendous success of large language models (LLMs), researchers have begun to explore utilizing LLMs for generating RTL code. However, current studies primarily focus on generating simple single modules, which can not meet the demands in real world. In fact, due to challenges in managing long-context RTL code and complex cross-file dependencies, existing solutions cannot handle large-scale Verilog repositories in practical hardware developm"},"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":"2504.08862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-11T09:04:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad74f173d41f21b9c46ed35c4417eb982a04876da0493f5a3b3f6434fba1bd9e","abstract_canon_sha256":"0d0c961ab7958548d1e28c7e28dec47de9113ecd66b81b2bd9db070e53d6d61d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:00.565788Z","signature_b64":"ba/sVVI3QAVk1fbl/FmQRVsTdRLV7luNT/LI57r16EaeyIOCZyhNqS9b4SrWTVvmbBpJ/qhqz/6ANA6vqT1BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4bc21aa2c6cffacd72206cc65dca3a6c53ff26f168a94b5498975ab8c34a945","last_reissued_at":"2026-07-05T10:48:00.565319Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:00.565319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Junliang Lv, Nan Guo, Peiyang Wu, Xiaochun Ye, Xiao Xiao","submitted_at":"2025-04-11T09:04:50Z","abstract_excerpt":"As an essential part of modern hardware design, manually writing Register Transfer Level (RTL) code such as Verilog is often labor-intensive. Following the tremendous success of large language models (LLMs), researchers have begun to explore utilizing LLMs for generating RTL code. However, current studies primarily focus on generating simple single modules, which can not meet the demands in real world. In fact, due to challenges in managing long-context RTL code and complex cross-file dependencies, existing solutions cannot handle large-scale Verilog repositories in practical hardware developm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08862","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/2504.08862/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":"2504.08862","created_at":"2026-07-05T10:48:00.565375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08862v1","created_at":"2026-07-05T10:48:00.565375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08862","created_at":"2026-07-05T10:48:00.565375+00:00"},{"alias_kind":"pith_short_12","alias_value":"YS6CDKRMNT72","created_at":"2026-07-05T10:48:00.565375+00:00"},{"alias_kind":"pith_short_16","alias_value":"YS6CDKRMNT72ZVZC","created_at":"2026-07-05T10:48:00.565375+00:00"},{"alias_kind":"pith_short_8","alias_value":"YS6CDKRM","created_at":"2026-07-05T10:48:00.565375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3","json":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3.json","graph_json":"https://pith.science/api/pith-number/YS6CDKRMNT72ZVZCA3GGLXFDU3/graph.json","events_json":"https://pith.science/api/pith-number/YS6CDKRMNT72ZVZCA3GGLXFDU3/events.json","paper":"https://pith.science/paper/YS6CDKRM"},"agent_actions":{"view_html":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3","download_json":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3.json","view_paper":"https://pith.science/paper/YS6CDKRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08862&json=true","fetch_graph":"https://pith.science/api/pith-number/YS6CDKRMNT72ZVZCA3GGLXFDU3/graph.json","fetch_events":"https://pith.science/api/pith-number/YS6CDKRMNT72ZVZCA3GGLXFDU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3/action/storage_attestation","attest_author":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3/action/author_attestation","sign_citation":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3/action/citation_signature","submit_replication":"https://pith.science/pith/YS6CDKRMNT72ZVZCA3GGLXFDU3/action/replication_record"}},"created_at":"2026-07-05T10:48:00.565375+00:00","updated_at":"2026-07-05T10:48:00.565375+00:00"}