{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NVRAO7N6K43QYYWV4DCI5MLP2S","short_pith_number":"pith:NVRAO7N6","schema_version":"1.0","canonical_sha256":"6d62077dbe57370c62d5e0c48eb16fd48a844f9aaec799b2c0cf3a10d71426c7","source":{"kind":"arxiv","id":"2608.00326","version":1},"attestation_state":"computed","paper":{"title":"Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares Certificates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohan Chen, Richard Hoffmann, Sam Looi, Shivam N. Patel, Tony Yue Yu","submitted_at":"2026-07-31T22:26:45Z","abstract_excerpt":"Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields including AI for mathematics. We study this setting through weighted sum-of-squares (SOS) decomposition, a machine-checkable route to proving polynomial nonnegativity and hence polynomial inequalities. A candidate decomposition can be checked exactly, but finding one requires choosing among non-unique regroupings and coordinating multiple symbolic transformations. We develop an agent that combines algebraic task training, symbolic tools, and verifier-gro"},"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":"2608.00326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T22:26:45Z","cross_cats_sorted":[],"title_canon_sha256":"39c61535184d43f399633335f560c322be2c194ef241690420a685d0c71d2da7","abstract_canon_sha256":"6357894074f30c1ff208c20d6f4ca5c611fd18f87709ded106bd203f0177a73f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:35:06.353260Z","signature_b64":"ZgnpdaYJzs9b9T0VcFYEXc8juMk0LC3LbonQdFvMhjzTD8agwt345+cvW8V9NMSL7Z/wIEZsHtsQ5vXwn0SwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d62077dbe57370c62d5e0c48eb16fd48a844f9aaec799b2c0cf3a10d71426c7","last_reissued_at":"2026-08-04T00:35:06.351908Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:35:06.351908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares Certificates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohan Chen, Richard Hoffmann, Sam Looi, Shivam N. Patel, Tony Yue Yu","submitted_at":"2026-07-31T22:26:45Z","abstract_excerpt":"Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields including AI for mathematics. We study this setting through weighted sum-of-squares (SOS) decomposition, a machine-checkable route to proving polynomial nonnegativity and hence polynomial inequalities. A candidate decomposition can be checked exactly, but finding one requires choosing among non-unique regroupings and coordinating multiple symbolic transformations. We develop an agent that combines algebraic task training, symbolic tools, and verifier-gro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00326","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/2608.00326/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":"2608.00326","created_at":"2026-08-04T00:35:06.352975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00326v1","created_at":"2026-08-04T00:35:06.352975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00326","created_at":"2026-08-04T00:35:06.352975+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVRAO7N6K43Q","created_at":"2026-08-04T00:35:06.352975+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVRAO7N6K43QYYWV","created_at":"2026-08-04T00:35:06.352975+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVRAO7N6","created_at":"2026-08-04T00:35:06.352975+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/NVRAO7N6K43QYYWV4DCI5MLP2S","json":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S.json","graph_json":"https://pith.science/api/pith-number/NVRAO7N6K43QYYWV4DCI5MLP2S/graph.json","events_json":"https://pith.science/api/pith-number/NVRAO7N6K43QYYWV4DCI5MLP2S/events.json","paper":"https://pith.science/paper/NVRAO7N6"},"agent_actions":{"view_html":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S","download_json":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S.json","view_paper":"https://pith.science/paper/NVRAO7N6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00326&json=true","fetch_graph":"https://pith.science/api/pith-number/NVRAO7N6K43QYYWV4DCI5MLP2S/graph.json","fetch_events":"https://pith.science/api/pith-number/NVRAO7N6K43QYYWV4DCI5MLP2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S/action/storage_attestation","attest_author":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S/action/author_attestation","sign_citation":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S/action/citation_signature","submit_replication":"https://pith.science/pith/NVRAO7N6K43QYYWV4DCI5MLP2S/action/replication_record"}},"created_at":"2026-08-04T00:35:06.352975+00:00","updated_at":"2026-08-04T00:35:06.352975+00:00"}