{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QVFO45RI4O4J2CXYBLJMRYVKV","short_pith_number":"pith:5QVFO45R","schema_version":"1.0","canonical_sha256":"ec2a5773b1471dc4e857c0569647155565231a5c690f0dbde2313a6c264bce04","source":{"kind":"arxiv","id":"2408.06810","version":1},"attestation_state":"computed","paper":{"title":"HLSPilot: LLM-based High-Level Synthesis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Cheng Liu, Chenwei Xiong, Huawei Li, Xiaowei Li","submitted_at":"2024-08-13T10:59:30Z","abstract_excerpt":"Large language models (LLMs) have catalyzed an upsurge in automatic code generation, garnering significant attention for register transfer level (RTL) code generation. Despite the potential of RTL code generation with natural language, it remains error-prone and limited to relatively small modules because of the substantial semantic gap between natural language expressions and hardware design intent. In response to the limitations, we propose a methodology that reduces the semantic gaps by utilizing C/C++ for generating hardware designs via High-Level Synthesis (HLS) tools. Basically, we build"},"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":"2408.06810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AR","submitted_at":"2024-08-13T10:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"26b3af19a777c0044c87dbfe5f58b10057e80f9596d3b07231cb30d02af60156","abstract_canon_sha256":"223de1d3b6b8b53cf360d6219a2b157daeeec6762e8bb69b61fede17bd095910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:02.130258Z","signature_b64":"WkJmVaeAH56L+eH9qRsquEKO9bQJnPc8wOJkJZRSmd2Tm14exG1FnP8QkcxRKo8kTTufgwLt3xDXf9e0Eij6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2a5773b1471dc4e857c0569647155565231a5c690f0dbde2313a6c264bce04","last_reissued_at":"2026-07-05T08:55:02.129849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:02.129849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HLSPilot: LLM-based High-Level Synthesis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Cheng Liu, Chenwei Xiong, Huawei Li, Xiaowei Li","submitted_at":"2024-08-13T10:59:30Z","abstract_excerpt":"Large language models (LLMs) have catalyzed an upsurge in automatic code generation, garnering significant attention for register transfer level (RTL) code generation. Despite the potential of RTL code generation with natural language, it remains error-prone and limited to relatively small modules because of the substantial semantic gap between natural language expressions and hardware design intent. In response to the limitations, we propose a methodology that reduces the semantic gaps by utilizing C/C++ for generating hardware designs via High-Level Synthesis (HLS) tools. Basically, we build"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06810","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/2408.06810/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":"2408.06810","created_at":"2026-07-05T08:55:02.129903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06810v1","created_at":"2026-07-05T08:55:02.129903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06810","created_at":"2026-07-05T08:55:02.129903+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QVFO45RI4O4","created_at":"2026-07-05T08:55:02.129903+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QVFO45RI4O4J2CX","created_at":"2026-07-05T08:55:02.129903+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QVFO45R","created_at":"2026-07-05T08:55:02.129903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17128","citing_title":"Shift-Left High-Level Synthesis Verification via Knowledge-Augmented LLM Agent","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25719","citing_title":"Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13536","citing_title":"HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV","json":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV.json","graph_json":"https://pith.science/api/pith-number/5QVFO45RI4O4J2CXYBLJMRYVKV/graph.json","events_json":"https://pith.science/api/pith-number/5QVFO45RI4O4J2CXYBLJMRYVKV/events.json","paper":"https://pith.science/paper/5QVFO45R"},"agent_actions":{"view_html":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV","download_json":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV.json","view_paper":"https://pith.science/paper/5QVFO45R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06810&json=true","fetch_graph":"https://pith.science/api/pith-number/5QVFO45RI4O4J2CXYBLJMRYVKV/graph.json","fetch_events":"https://pith.science/api/pith-number/5QVFO45RI4O4J2CXYBLJMRYVKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV/action/storage_attestation","attest_author":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV/action/author_attestation","sign_citation":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV/action/citation_signature","submit_replication":"https://pith.science/pith/5QVFO45RI4O4J2CXYBLJMRYVKV/action/replication_record"}},"created_at":"2026-07-05T08:55:02.129903+00:00","updated_at":"2026-07-05T08:55:02.129903+00:00"}