{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JQZ3IKJQVUGPE7YIJQW5YIBEVZ","short_pith_number":"pith:JQZ3IKJQ","schema_version":"1.0","canonical_sha256":"4c33b42930ad0cf27f084c2ddc2024ae49bf1d7d270350f53090549180abbef6","source":{"kind":"arxiv","id":"2608.12751","version":1},"attestation_state":"computed","paper":{"title":"SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Bei Yu, Fangzhou Liu, Jiawei Liu, Peiyi Han, Rongliang Fu, Tsung-Yi Ho, Yuan Pu, Zhuolun He","submitted_at":"2026-08-13T03:02:25Z","abstract_excerpt":"Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis"},"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":"2608.12751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-08-13T03:02:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab2f909f99d5c1701b3acf868b354d3f61558d6bc8020c7d0e665903c75b9fa3","abstract_canon_sha256":"635251d8eb94a02d0588f81ace07644356488de2de5533332f42f82e302f8e7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:30.395179Z","signature_b64":"z6hDWk29j4f4281MW8Oe6NBOdQwgZh6biaqVdrYbdWOWA4Iuw9ATscJYHd8eq1Nqum1sKfoW3C27jFdEP6ZaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c33b42930ad0cf27f084c2ddc2024ae49bf1d7d270350f53090549180abbef6","last_reissued_at":"2026-08-14T00:47:30.393150Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:30.393150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Bei Yu, Fangzhou Liu, Jiawei Liu, Peiyi Han, Rongliang Fu, Tsung-Yi Ho, Yuan Pu, Zhuolun He","submitted_at":"2026-08-13T03:02:25Z","abstract_excerpt":"Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12751","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/2608.12751/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":"2608.12751","created_at":"2026-08-14T00:47:30.394100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12751v1","created_at":"2026-08-14T00:47:30.394100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12751","created_at":"2026-08-14T00:47:30.394100+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQZ3IKJQVUGP","created_at":"2026-08-14T00:47:30.394100+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQZ3IKJQVUGPE7YI","created_at":"2026-08-14T00:47:30.394100+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQZ3IKJQ","created_at":"2026-08-14T00:47:30.394100+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/JQZ3IKJQVUGPE7YIJQW5YIBEVZ","json":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ.json","graph_json":"https://pith.science/api/pith-number/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/graph.json","events_json":"https://pith.science/api/pith-number/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/events.json","paper":"https://pith.science/paper/JQZ3IKJQ"},"agent_actions":{"view_html":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ","download_json":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ.json","view_paper":"https://pith.science/paper/JQZ3IKJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12751&json=true","fetch_graph":"https://pith.science/api/pith-number/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/action/storage_attestation","attest_author":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/action/author_attestation","sign_citation":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/action/citation_signature","submit_replication":"https://pith.science/pith/JQZ3IKJQVUGPE7YIJQW5YIBEVZ/action/replication_record"}},"created_at":"2026-08-14T00:47:30.394100+00:00","updated_at":"2026-08-14T00:47:30.394100+00:00"}