{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WAYTLBUNLYKLZJHDJTSLCQPASP","short_pith_number":"pith:WAYTLBUN","schema_version":"1.0","canonical_sha256":"b03135868d5e14bca4e34ce4b141e093e549fa8f2a1bbf259de9da07ee53ea08","source":{"kind":"arxiv","id":"2605.15131","version":1},"attestation_state":"computed","paper":{"title":"Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernd Finkbeiner, Frederik Schmitt, Julian Siber, Matthias Cosler, Mohamed Ghanem, Niklas Metzger, Vladimir Krsmanovic","submitted_at":"2026-05-14T17:39:58Z","abstract_excerpt":"Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive for two reasons: It is algorithmically hard, and writing formal specifications by hand is notoriously difficult. In this paper, we tackle both sides of the problem. For the algorithmic side, we present a neuro-symbolic approach to reactive synthesis that couples large reasoning models with model checkers to iteratively repair a synthesized Verilog implementation via sound symbolic feedback. Our approach solves more ben"},"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":"2605.15131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:39:58Z","cross_cats_sorted":[],"title_canon_sha256":"7557f5e38ae2c1f7ca0e4eaf4865e613a734c2bb819857bbfe64b935948fc8fd","abstract_canon_sha256":"9f9792bb57003bfd1b24f8dfb80ef16aef9fedf36a74aa1112c54b9b56ae49f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:54.040078Z","signature_b64":"5YMG21luMYtcFwDJ7crBBz+BfjFr4HCAqIlJrEKLJy3yZ/bO9QSXGl11HeJxADbD6k872/t35gEgNkbO7eT2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b03135868d5e14bca4e34ce4b141e093e549fa8f2a1bbf259de9da07ee53ea08","last_reissued_at":"2026-05-17T23:38:54.039392Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:54.039392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernd Finkbeiner, Frederik Schmitt, Julian Siber, Matthias Cosler, Mohamed Ghanem, Niklas Metzger, Vladimir Krsmanovic","submitted_at":"2026-05-14T17:39:58Z","abstract_excerpt":"Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive for two reasons: It is algorithmically hard, and writing formal specifications by hand is notoriously difficult. In this paper, we tackle both sides of the problem. For the algorithmic side, we present a neuro-symbolic approach to reactive synthesis that couples large reasoning models with model checkers to iteratively repair a synthesized Verilog implementation via sound symbolic feedback. Our approach solves more ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15131","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":""},"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":"2605.15131","created_at":"2026-05-17T23:38:54.039504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15131v1","created_at":"2026-05-17T23:38:54.039504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15131","created_at":"2026-05-17T23:38:54.039504+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAYTLBUNLYKL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAYTLBUNLYKLZJHD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAYTLBUN","created_at":"2026-05-18T12:33:37.589309+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/WAYTLBUNLYKLZJHDJTSLCQPASP","json":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP.json","graph_json":"https://pith.science/api/pith-number/WAYTLBUNLYKLZJHDJTSLCQPASP/graph.json","events_json":"https://pith.science/api/pith-number/WAYTLBUNLYKLZJHDJTSLCQPASP/events.json","paper":"https://pith.science/paper/WAYTLBUN"},"agent_actions":{"view_html":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP","download_json":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP.json","view_paper":"https://pith.science/paper/WAYTLBUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15131&json=true","fetch_graph":"https://pith.science/api/pith-number/WAYTLBUNLYKLZJHDJTSLCQPASP/graph.json","fetch_events":"https://pith.science/api/pith-number/WAYTLBUNLYKLZJHDJTSLCQPASP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP/action/storage_attestation","attest_author":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP/action/author_attestation","sign_citation":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP/action/citation_signature","submit_replication":"https://pith.science/pith/WAYTLBUNLYKLZJHDJTSLCQPASP/action/replication_record"}},"created_at":"2026-05-17T23:38:54.039504+00:00","updated_at":"2026-05-17T23:38:54.039504+00:00"}