{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:55FZIWRNQ2ZKVURVWAGD2UBA5I","short_pith_number":"pith:55FZIWRN","schema_version":"1.0","canonical_sha256":"ef4b945a2d86b2aad235b00c3d5020ea2d73bfebe9abe58c9644b60fa9a7f038","source":{"kind":"arxiv","id":"2405.17378","version":1},"attestation_state":"computed","paper":{"title":"RTL-Repo: A Benchmark for Evaluating LLMs on Large-Scale RTL Design Projects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Ahmed Allam, Mohamed Shalan","submitted_at":"2024-05-27T17:36:01Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated potential in assisting with Register Transfer Level (RTL) design tasks. Nevertheless, there remains to be a significant gap in benchmarks that accurately reflect the complexity of real-world RTL projects. To address this, this paper presents RTL-Repo, a benchmark specifically designed to evaluate LLMs on large-scale RTL design projects. RTL-Repo includes a comprehensive dataset of more than 4000 Verilog code samples extracted from public GitHub repositories, with each sample providing the full context of the corresponding repository. We evaluate s"},"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":"2405.17378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T17:36:01Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"f5cd8cfd9d535b827f3ca9934da5975c37fc2bee89b4bece739f4bfc1d992a12","abstract_canon_sha256":"9c171c11352674622e77c0cb32aab70635ad52f8cb8868c05233efeeb3b09a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:43.749992Z","signature_b64":"ZoXRr0IAPzKN1BRX0PEdfVjjbLf0Lh9OqcOQbXmdbW9YQztNgJaO3wz6pyB8lbLfYFRKTLfEyRfIhXDy2ptxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef4b945a2d86b2aad235b00c3d5020ea2d73bfebe9abe58c9644b60fa9a7f038","last_reissued_at":"2026-07-05T08:23:43.749346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:43.749346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTL-Repo: A Benchmark for Evaluating LLMs on Large-Scale RTL Design Projects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Ahmed Allam, Mohamed Shalan","submitted_at":"2024-05-27T17:36:01Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated potential in assisting with Register Transfer Level (RTL) design tasks. Nevertheless, there remains to be a significant gap in benchmarks that accurately reflect the complexity of real-world RTL projects. To address this, this paper presents RTL-Repo, a benchmark specifically designed to evaluate LLMs on large-scale RTL design projects. RTL-Repo includes a comprehensive dataset of more than 4000 Verilog code samples extracted from public GitHub repositories, with each sample providing the full context of the corresponding repository. We evaluate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17378","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/2405.17378/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":"2405.17378","created_at":"2026-07-05T08:23:43.749463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17378v1","created_at":"2026-07-05T08:23:43.749463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17378","created_at":"2026-07-05T08:23:43.749463+00:00"},{"alias_kind":"pith_short_12","alias_value":"55FZIWRNQ2ZK","created_at":"2026-07-05T08:23:43.749463+00:00"},{"alias_kind":"pith_short_16","alias_value":"55FZIWRNQ2ZKVURV","created_at":"2026-07-05T08:23:43.749463+00:00"},{"alias_kind":"pith_short_8","alias_value":"55FZIWRN","created_at":"2026-07-05T08:23:43.749463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14989","citing_title":"Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I","json":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I.json","graph_json":"https://pith.science/api/pith-number/55FZIWRNQ2ZKVURVWAGD2UBA5I/graph.json","events_json":"https://pith.science/api/pith-number/55FZIWRNQ2ZKVURVWAGD2UBA5I/events.json","paper":"https://pith.science/paper/55FZIWRN"},"agent_actions":{"view_html":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I","download_json":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I.json","view_paper":"https://pith.science/paper/55FZIWRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17378&json=true","fetch_graph":"https://pith.science/api/pith-number/55FZIWRNQ2ZKVURVWAGD2UBA5I/graph.json","fetch_events":"https://pith.science/api/pith-number/55FZIWRNQ2ZKVURVWAGD2UBA5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I/action/storage_attestation","attest_author":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I/action/author_attestation","sign_citation":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I/action/citation_signature","submit_replication":"https://pith.science/pith/55FZIWRNQ2ZKVURVWAGD2UBA5I/action/replication_record"}},"created_at":"2026-07-05T08:23:43.749463+00:00","updated_at":"2026-07-05T08:23:43.749463+00:00"}