{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7X66SRR57K5S2QUF6O65LXHWIL","short_pith_number":"pith:7X66SRR5","schema_version":"1.0","canonical_sha256":"fdfde9463dfabb2d4285f3bdd5dcf642ca1cbbb8a464982598136125cdb163ce","source":{"kind":"arxiv","id":"2606.30949","version":1},"attestation_state":"computed","paper":{"title":"AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.AI","authors_text":"Jason Cong, Yang Zou, Yizhou Sun, Zijian Ding","submitted_at":"2026-06-29T22:02:34Z","abstract_excerpt":"High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs. AgRefactor incorporates a self-evolving memory syste"},"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":"2606.30949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T22:02:34Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"27c0b37492471205ce61a8e3651f525ea77047d3fddde304d536421208ab4ef2","abstract_canon_sha256":"16961a1e891d044ae257c142f4470fc11aaeb1d6fc19cb6a9630913ec544e6d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:22.511527Z","signature_b64":"IS+bbOxv2irxibYBamzqpCTmUwSWh7i+Nuezsq/J3nGu8fDwbOeHxIxQ9jQu1WXtaIMwtnJHFm7cigX+cnXdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdfde9463dfabb2d4285f3bdd5dcf642ca1cbbb8a464982598136125cdb163ce","last_reissued_at":"2026-07-01T00:17:22.510959Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:22.510959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.AI","authors_text":"Jason Cong, Yang Zou, Yizhou Sun, Zijian Ding","submitted_at":"2026-06-29T22:02:34Z","abstract_excerpt":"High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs. AgRefactor incorporates a self-evolving memory syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30949","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/2606.30949/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":"2606.30949","created_at":"2026-07-01T00:17:22.511034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30949v1","created_at":"2026-07-01T00:17:22.511034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30949","created_at":"2026-07-01T00:17:22.511034+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X66SRR57K5S","created_at":"2026-07-01T00:17:22.511034+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X66SRR57K5S2QUF","created_at":"2026-07-01T00:17:22.511034+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X66SRR5","created_at":"2026-07-01T00:17:22.511034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL","json":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL.json","graph_json":"https://pith.science/api/pith-number/7X66SRR57K5S2QUF6O65LXHWIL/graph.json","events_json":"https://pith.science/api/pith-number/7X66SRR57K5S2QUF6O65LXHWIL/events.json","paper":"https://pith.science/paper/7X66SRR5"},"agent_actions":{"view_html":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL","download_json":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL.json","view_paper":"https://pith.science/paper/7X66SRR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30949&json=true","fetch_graph":"https://pith.science/api/pith-number/7X66SRR57K5S2QUF6O65LXHWIL/graph.json","fetch_events":"https://pith.science/api/pith-number/7X66SRR57K5S2QUF6O65LXHWIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL/action/storage_attestation","attest_author":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL/action/author_attestation","sign_citation":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL/action/citation_signature","submit_replication":"https://pith.science/pith/7X66SRR57K5S2QUF6O65LXHWIL/action/replication_record"}},"created_at":"2026-07-01T00:17:22.511034+00:00","updated_at":"2026-07-01T00:17:22.511034+00:00"}