{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S7E2K6CYMHQP3XN6WMCG7T3T6I","short_pith_number":"pith:S7E2K6CY","schema_version":"1.0","canonical_sha256":"97c9a5785861e0fdddbeb3046fcf73f228197cea862b9801d12acc8408ab3404","source":{"kind":"arxiv","id":"2606.07704","version":1},"attestation_state":"computed","paper":{"title":"FunctionEvolve: Structure-Guided Symbolic Regression with LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dong Yan, Jun Zhu, Zeyu Xia","submitted_at":"2026-06-05T09:18:01Z","abstract_excerpt":"Symbolic regression aims to uncover explicit scientific laws from data. Recent methods use LLMs to guide mutation from background text, which is more directed than random genetic programming. However, exact symbolic recovery requires both semantic guidance and explicit structure, so that domain-informed search are carried out through valid symbolic representation. Current LLM-driven systems remain structure-blind: they select among opaque candidates, lack explicit mechanisms for local mutation, and rely on brittle coefficient fitting that can undervalue correct skeletons. We propose FunctionEv"},"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":"2606.07704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T09:18:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa5e6920e5165dd1cd3e24a10e6f357a6b901c1fae4ffb72953376e71833190d","abstract_canon_sha256":"f476422f6307e89753d7068f8262e012c0ebd8e2ea14cf1864f6b76c6e68d463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:49.751446Z","signature_b64":"hqKtlY+23ailsIvIhJIQdjLPLZRVtA98BqzOyp4l+FmAra9PU2lW5HRSJRXUn8+XJEjylRPFImR39Fa1gs+XDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c9a5785861e0fdddbeb3046fcf73f228197cea862b9801d12acc8408ab3404","last_reissued_at":"2026-06-09T01:04:49.751015Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:49.751015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FunctionEvolve: Structure-Guided Symbolic Regression with LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dong Yan, Jun Zhu, Zeyu Xia","submitted_at":"2026-06-05T09:18:01Z","abstract_excerpt":"Symbolic regression aims to uncover explicit scientific laws from data. Recent methods use LLMs to guide mutation from background text, which is more directed than random genetic programming. However, exact symbolic recovery requires both semantic guidance and explicit structure, so that domain-informed search are carried out through valid symbolic representation. Current LLM-driven systems remain structure-blind: they select among opaque candidates, lack explicit mechanisms for local mutation, and rely on brittle coefficient fitting that can undervalue correct skeletons. We propose FunctionEv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07704","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/2606.07704/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":"2606.07704","created_at":"2026-06-09T01:04:49.751084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07704v1","created_at":"2026-06-09T01:04:49.751084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07704","created_at":"2026-06-09T01:04:49.751084+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7E2K6CYMHQP","created_at":"2026-06-09T01:04:49.751084+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7E2K6CYMHQP3XN6","created_at":"2026-06-09T01:04:49.751084+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7E2K6CY","created_at":"2026-06-09T01:04:49.751084+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/S7E2K6CYMHQP3XN6WMCG7T3T6I","json":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I.json","graph_json":"https://pith.science/api/pith-number/S7E2K6CYMHQP3XN6WMCG7T3T6I/graph.json","events_json":"https://pith.science/api/pith-number/S7E2K6CYMHQP3XN6WMCG7T3T6I/events.json","paper":"https://pith.science/paper/S7E2K6CY"},"agent_actions":{"view_html":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I","download_json":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I.json","view_paper":"https://pith.science/paper/S7E2K6CY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/S7E2K6CYMHQP3XN6WMCG7T3T6I/graph.json","fetch_events":"https://pith.science/api/pith-number/S7E2K6CYMHQP3XN6WMCG7T3T6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I/action/storage_attestation","attest_author":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I/action/author_attestation","sign_citation":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I/action/citation_signature","submit_replication":"https://pith.science/pith/S7E2K6CYMHQP3XN6WMCG7T3T6I/action/replication_record"}},"created_at":"2026-06-09T01:04:49.751084+00:00","updated_at":"2026-06-09T01:04:49.751084+00:00"}