{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CE3WEWOJCX43PJEDFXN4EEUHLB","short_pith_number":"pith:CE3WEWOJ","schema_version":"1.0","canonical_sha256":"11376259c915f9b7a4832ddbc212875871d4ea6a503b5dd0240f3142b80a75ee","source":{"kind":"arxiv","id":"2502.18297","version":1},"attestation_state":"computed","paper":{"title":"DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Changran Xu, Chengyu Ma, Jianyuan Zhong, Jieru Zhao, Lingfeng Zhou, Qiang Xu, Xiaoyan Yang, Xi Wang, Yi Liu, Yunhao Zhou, Zedong Peng, Zeju Li, Zhengyuan Shi, Zhufei Chu","submitted_at":"2025-02-25T15:34:00Z","abstract_excerpt":"This paper introduces DeepCircuitX, a comprehensive repository-level dataset designed to advance RTL (Register Transfer Level) code understanding, generation, and power-performance-area (PPA) analysis. Unlike existing datasets that are limited to either file-level RTL code or physical layout data, DeepCircuitX provides a holistic, multilevel resource that spans repository, file, module, and block-level RTL code. This structure enables more nuanced training and evaluation of large language models (LLMs) for RTL-specific tasks. DeepCircuitX is enriched with Chain of Thought (CoT) annotations, of"},"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":"2502.18297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T15:34:00Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"222cc31b1b898c7bd7f134b3c9af6da6750315e22d006ad6aff9d346d6bd07b8","abstract_canon_sha256":"281d4246ef7c4511a58070dea3f9ee850982db55cb4ee76aa298d43a77b61211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:51.846479Z","signature_b64":"vatum8uXQE0FEc8yZLLsJRHJ2IwJyRVl7AHc41gFYlDFzqN5P24vS6QnC4U8yGU5r6T7El/wzYmTpsJRxwvyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11376259c915f9b7a4832ddbc212875871d4ea6a503b5dd0240f3142b80a75ee","last_reissued_at":"2026-07-05T10:19:51.845968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:51.845968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Changran Xu, Chengyu Ma, Jianyuan Zhong, Jieru Zhao, Lingfeng Zhou, Qiang Xu, Xiaoyan Yang, Xi Wang, Yi Liu, Yunhao Zhou, Zedong Peng, Zeju Li, Zhengyuan Shi, Zhufei Chu","submitted_at":"2025-02-25T15:34:00Z","abstract_excerpt":"This paper introduces DeepCircuitX, a comprehensive repository-level dataset designed to advance RTL (Register Transfer Level) code understanding, generation, and power-performance-area (PPA) analysis. Unlike existing datasets that are limited to either file-level RTL code or physical layout data, DeepCircuitX provides a holistic, multilevel resource that spans repository, file, module, and block-level RTL code. This structure enables more nuanced training and evaluation of large language models (LLMs) for RTL-specific tasks. DeepCircuitX is enriched with Chain of Thought (CoT) annotations, of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18297","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/2502.18297/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":"2502.18297","created_at":"2026-07-05T10:19:51.846035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18297v1","created_at":"2026-07-05T10:19:51.846035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18297","created_at":"2026-07-05T10:19:51.846035+00:00"},{"alias_kind":"pith_short_12","alias_value":"CE3WEWOJCX43","created_at":"2026-07-05T10:19:51.846035+00:00"},{"alias_kind":"pith_short_16","alias_value":"CE3WEWOJCX43PJED","created_at":"2026-07-05T10:19:51.846035+00:00"},{"alias_kind":"pith_short_8","alias_value":"CE3WEWOJ","created_at":"2026-07-05T10:19:51.846035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08976","citing_title":"RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23602","citing_title":"TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB","json":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB.json","graph_json":"https://pith.science/api/pith-number/CE3WEWOJCX43PJEDFXN4EEUHLB/graph.json","events_json":"https://pith.science/api/pith-number/CE3WEWOJCX43PJEDFXN4EEUHLB/events.json","paper":"https://pith.science/paper/CE3WEWOJ"},"agent_actions":{"view_html":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB","download_json":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB.json","view_paper":"https://pith.science/paper/CE3WEWOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18297&json=true","fetch_graph":"https://pith.science/api/pith-number/CE3WEWOJCX43PJEDFXN4EEUHLB/graph.json","fetch_events":"https://pith.science/api/pith-number/CE3WEWOJCX43PJEDFXN4EEUHLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB/action/storage_attestation","attest_author":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB/action/author_attestation","sign_citation":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB/action/citation_signature","submit_replication":"https://pith.science/pith/CE3WEWOJCX43PJEDFXN4EEUHLB/action/replication_record"}},"created_at":"2026-07-05T10:19:51.846035+00:00","updated_at":"2026-07-05T10:19:51.846035+00:00"}