{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HVCXXN47U23RGSXETAM4YJKC5Q","short_pith_number":"pith:HVCXXN47","schema_version":"1.0","canonical_sha256":"3d457bb79fa6b7134ae49819cc2542ec02f5eaeccde3c0450ae5feb87b244cf3","source":{"kind":"arxiv","id":"2505.22086","version":2},"attestation_state":"computed","paper":{"title":"iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Jia Xiong, Runkai Li, Xi Wang","submitted_at":"2025-05-28T08:08:57Z","abstract_excerpt":"High-Level Synthesis (HLS) serves as an agile hardware development tool that streamlines the circuit design by abstracting the register transfer level into behavioral descriptions, while allowing designers to customize the generated microarchitectures through optimization directives. However, the combinatorial explosion of possible directive configurations yields an intractable design space. Traditional design space exploration (DSE) methods, despite adopting heuristics or constructing predictive models to accelerate Pareto-optimal design acquisition, still suffer from prohibitive exploration "},"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":"2505.22086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-05-28T08:08:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4fd0cf9085dd393e40fd945ce5b3cee43b2db942af0198eb02e401a5c6b9e622","abstract_canon_sha256":"64c8f85913ca46711f7ca90fb33ff792e1361152f342e9802172cb8fa3551c95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:27.279371Z","signature_b64":"EUEKhYWjfXJ32+P9RU7LnqHkJC4o1B06X2kmoAc7G2p70tKmmZcUKsgh3qMx2AuSWVhn+RN7w3D4otVSsg/uCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d457bb79fa6b7134ae49819cc2542ec02f5eaeccde3c0450ae5feb87b244cf3","last_reissued_at":"2026-07-05T11:13:27.278892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:27.278892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Jia Xiong, Runkai Li, Xi Wang","submitted_at":"2025-05-28T08:08:57Z","abstract_excerpt":"High-Level Synthesis (HLS) serves as an agile hardware development tool that streamlines the circuit design by abstracting the register transfer level into behavioral descriptions, while allowing designers to customize the generated microarchitectures through optimization directives. However, the combinatorial explosion of possible directive configurations yields an intractable design space. Traditional design space exploration (DSE) methods, despite adopting heuristics or constructing predictive models to accelerate Pareto-optimal design acquisition, still suffer from prohibitive exploration "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22086","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/2505.22086/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":"2505.22086","created_at":"2026-07-05T11:13:27.278949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22086v2","created_at":"2026-07-05T11:13:27.278949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22086","created_at":"2026-07-05T11:13:27.278949+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVCXXN47U23R","created_at":"2026-07-05T11:13:27.278949+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVCXXN47U23RGSXE","created_at":"2026-07-05T11:13:27.278949+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVCXXN47","created_at":"2026-07-05T11:13:27.278949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11117","citing_title":"Towards Autonomous Accelerator Design: FPGA Accelerator Generation with SECDA","ref_index":12,"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":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24218","citing_title":"RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05920","citing_title":"LLM-Driven Design Space Exploration of FPGA-based Accelerators","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11044","citing_title":"Automated SVA Generation with LLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15642","citing_title":"HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q","json":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q.json","graph_json":"https://pith.science/api/pith-number/HVCXXN47U23RGSXETAM4YJKC5Q/graph.json","events_json":"https://pith.science/api/pith-number/HVCXXN47U23RGSXETAM4YJKC5Q/events.json","paper":"https://pith.science/paper/HVCXXN47"},"agent_actions":{"view_html":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q","download_json":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q.json","view_paper":"https://pith.science/paper/HVCXXN47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22086&json=true","fetch_graph":"https://pith.science/api/pith-number/HVCXXN47U23RGSXETAM4YJKC5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/HVCXXN47U23RGSXETAM4YJKC5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q/action/storage_attestation","attest_author":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q/action/author_attestation","sign_citation":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q/action/citation_signature","submit_replication":"https://pith.science/pith/HVCXXN47U23RGSXETAM4YJKC5Q/action/replication_record"}},"created_at":"2026-07-05T11:13:27.278949+00:00","updated_at":"2026-07-05T11:13:27.278949+00:00"}