{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EJLQE5FPRTXD4MP4K47CYLZY3T","short_pith_number":"pith:EJLQE5FP","schema_version":"1.0","canonical_sha256":"22570274af8cee3e31fc573e2c2f38dcd04f75e6b2f30c98de69d5f6f6af986c","source":{"kind":"arxiv","id":"2507.16200","version":1},"attestation_state":"computed","paper":{"title":"RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Bohan Dou, Chongxiao Li, Di Huang, Jiaguo Zhu, Pengwei Jin, Qi Guo, Rui Zhang, Shuyao Cheng, Shuyi Xing, Xing Hu, Xinyao Zheng, Yang Zhao, Zidong Du","submitted_at":"2025-07-22T03:29:23Z","abstract_excerpt":"The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evaluating LLMs in Verilog generation fall short in replicating real-world design workflows due to their designs' simplicity, inadequate design specifications, and less rigorous verification environments. To address these limitations, we present RealBench, the first benchmark aiming at real-world IP-level Verilog generation tasks. RealBench features complex, structured, real-world open-source IP designs, multi-modal and fo"},"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":"2507.16200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T03:29:23Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"174824ca7807b2698e21b4acc0febe6d894068b2dd8680f047a7c90c191cf1ce","abstract_canon_sha256":"de1387dba0a5ce3ab6d9062230f5464f5fe9889daf16194fd47aa6acd20925e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:05.154565Z","signature_b64":"R5DMFKCbWmxE/B7jNzSXA8DVfr8VDWZNm3ehBZLx4xMYG3M2fZc4ch9XafziUHCS/2OXmzlC4lAH+Y3Ktfz5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22570274af8cee3e31fc573e2c2f38dcd04f75e6b2f30c98de69d5f6f6af986c","last_reissued_at":"2026-07-05T11:41:05.154128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:05.154128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Bohan Dou, Chongxiao Li, Di Huang, Jiaguo Zhu, Pengwei Jin, Qi Guo, Rui Zhang, Shuyao Cheng, Shuyi Xing, Xing Hu, Xinyao Zheng, Yang Zhao, Zidong Du","submitted_at":"2025-07-22T03:29:23Z","abstract_excerpt":"The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evaluating LLMs in Verilog generation fall short in replicating real-world design workflows due to their designs' simplicity, inadequate design specifications, and less rigorous verification environments. To address these limitations, we present RealBench, the first benchmark aiming at real-world IP-level Verilog generation tasks. RealBench features complex, structured, real-world open-source IP designs, multi-modal and fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16200","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/2507.16200/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":"2507.16200","created_at":"2026-07-05T11:41:05.154180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16200v1","created_at":"2026-07-05T11:41:05.154180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16200","created_at":"2026-07-05T11:41:05.154180+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJLQE5FPRTXD","created_at":"2026-07-05T11:41:05.154180+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJLQE5FPRTXD4MP4","created_at":"2026-07-05T11:41:05.154180+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJLQE5FP","created_at":"2026-07-05T11:41:05.154180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20456","citing_title":"Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03144","citing_title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27643","citing_title":"HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08932","citing_title":"From Indiscriminate to Targeted: Efficient RTL Verification via Functionally Key Signal-Driven LLM Assertion Generation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T","json":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T.json","graph_json":"https://pith.science/api/pith-number/EJLQE5FPRTXD4MP4K47CYLZY3T/graph.json","events_json":"https://pith.science/api/pith-number/EJLQE5FPRTXD4MP4K47CYLZY3T/events.json","paper":"https://pith.science/paper/EJLQE5FP"},"agent_actions":{"view_html":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T","download_json":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T.json","view_paper":"https://pith.science/paper/EJLQE5FP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16200&json=true","fetch_graph":"https://pith.science/api/pith-number/EJLQE5FPRTXD4MP4K47CYLZY3T/graph.json","fetch_events":"https://pith.science/api/pith-number/EJLQE5FPRTXD4MP4K47CYLZY3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T/action/storage_attestation","attest_author":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T/action/author_attestation","sign_citation":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T/action/citation_signature","submit_replication":"https://pith.science/pith/EJLQE5FPRTXD4MP4K47CYLZY3T/action/replication_record"}},"created_at":"2026-07-05T11:41:05.154180+00:00","updated_at":"2026-07-05T11:41:05.154180+00:00"}