{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BFTPH7PJCYT7CQQJXIIVESDMF2","short_pith_number":"pith:BFTPH7PJ","schema_version":"1.0","canonical_sha256":"0966f3fde91627f14209ba1152486c2ea32bb475a37862dd1dd145df3a4bc591","source":{"kind":"arxiv","id":"2503.12721","version":2},"attestation_state":"computed","paper":{"title":"Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Hennessee, Luca Collini, Ramesh Karri, Siddharth Garg","submitted_at":"2025-03-17T01:21:39Z","abstract_excerpt":"Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, a"},"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":"2503.12721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-17T01:21:39Z","cross_cats_sorted":[],"title_canon_sha256":"f927d76cd68e891efbd9667edd6920ac6c3e54193375696aebfa336c80b7a7d0","abstract_canon_sha256":"c546d900705bd6170485e2ff836c6e6b7155aa2f381a0881b8125ee2cead157f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:27.061236Z","signature_b64":"dV3wKuuQdwAMiBK+Gy9vNo7DxQrELqwlbuJJdpz3zh0vSsAhuSBWVxhrad7moJHY3uOGeGCNbOglXErLFOAgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0966f3fde91627f14209ba1152486c2ea32bb475a37862dd1dd145df3a4bc591","last_reissued_at":"2026-07-05T10:48:27.060698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:27.060698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Hennessee, Luca Collini, Ramesh Karri, Siddharth Garg","submitted_at":"2025-03-17T01:21:39Z","abstract_excerpt":"Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12721","kind":"arxiv","version":2},"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/2503.12721/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":"2503.12721","created_at":"2026-07-05T10:48:27.060761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12721v2","created_at":"2026-07-05T10:48:27.060761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12721","created_at":"2026-07-05T10:48:27.060761+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFTPH7PJCYT7","created_at":"2026-07-05T10:48:27.060761+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFTPH7PJCYT7CQQJ","created_at":"2026-07-05T10:48:27.060761+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFTPH7PJ","created_at":"2026-07-05T10:48:27.060761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10807","citing_title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2","json":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2.json","graph_json":"https://pith.science/api/pith-number/BFTPH7PJCYT7CQQJXIIVESDMF2/graph.json","events_json":"https://pith.science/api/pith-number/BFTPH7PJCYT7CQQJXIIVESDMF2/events.json","paper":"https://pith.science/paper/BFTPH7PJ"},"agent_actions":{"view_html":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2","download_json":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2.json","view_paper":"https://pith.science/paper/BFTPH7PJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12721&json=true","fetch_graph":"https://pith.science/api/pith-number/BFTPH7PJCYT7CQQJXIIVESDMF2/graph.json","fetch_events":"https://pith.science/api/pith-number/BFTPH7PJCYT7CQQJXIIVESDMF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2/action/storage_attestation","attest_author":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2/action/author_attestation","sign_citation":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2/action/citation_signature","submit_replication":"https://pith.science/pith/BFTPH7PJCYT7CQQJXIIVESDMF2/action/replication_record"}},"created_at":"2026-07-05T10:48:27.060761+00:00","updated_at":"2026-07-05T10:48:27.060761+00:00"}