{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4KVPXCPAKQ6WUJUTEOVTUMG5N7","short_pith_number":"pith:4KVPXCPA","schema_version":"1.0","canonical_sha256":"e2aafb89e0543d6a269323ab3a30dd6ffb8b4b2b1738c60e64171a914b93ed72","source":{"kind":"arxiv","id":"2606.04360","version":1},"attestation_state":"computed","paper":{"title":"Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Han, Changshui Zhang, Fangrui Lv, Sen Cui, Shanshan Wei, Xinyu Pang, Xuan Li, Zhanke Zhou","submitted_at":"2026-06-03T02:22:16Z","abstract_excerpt":"Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient because they rely mainly on scalar feedback such as MSE. We identify a core limitation: existing methods conflate candidate proposal with search guidance, requiring the LLM to infer how to evolve an expression, diagnose its errors, and reuse past experience from a single score. To address this, we propose Deliberate Evolution (DE), an agentic framework that decouples symbolic generation from search control. DE guides LLM proposals with adaptive oper"},"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":"2606.04360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T02:22:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f0ca646eda450b9aef12d38c569e0b403f112b339ceecd3000835f0a11cedfcf","abstract_canon_sha256":"9fd9f2661682140a70df0b40b3fabe0e8783be3eab77c5b2d559e4bbc99c9a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:05.198447Z","signature_b64":"xElCFTh0WWkIRc7RxVDeavbPThfJQUN+7nlESmv1IZggSlsSskEwk5UdexPp8eYQLtzPXiVESpZDqlIGpC30Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2aafb89e0543d6a269323ab3a30dd6ffb8b4b2b1738c60e64171a914b93ed72","last_reissued_at":"2026-06-04T01:09:05.197940Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:05.197940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Han, Changshui Zhang, Fangrui Lv, Sen Cui, Shanshan Wei, Xinyu Pang, Xuan Li, Zhanke Zhou","submitted_at":"2026-06-03T02:22:16Z","abstract_excerpt":"Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient because they rely mainly on scalar feedback such as MSE. We identify a core limitation: existing methods conflate candidate proposal with search guidance, requiring the LLM to infer how to evolve an expression, diagnose its errors, and reuse past experience from a single score. To address this, we propose Deliberate Evolution (DE), an agentic framework that decouples symbolic generation from search control. DE guides LLM proposals with adaptive oper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04360","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/2606.04360/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":"2606.04360","created_at":"2026-06-04T01:09:05.198025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04360v1","created_at":"2026-06-04T01:09:05.198025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04360","created_at":"2026-06-04T01:09:05.198025+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KVPXCPAKQ6W","created_at":"2026-06-04T01:09:05.198025+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KVPXCPAKQ6WUJUT","created_at":"2026-06-04T01:09:05.198025+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KVPXCPA","created_at":"2026-06-04T01:09:05.198025+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/4KVPXCPAKQ6WUJUTEOVTUMG5N7","json":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7.json","graph_json":"https://pith.science/api/pith-number/4KVPXCPAKQ6WUJUTEOVTUMG5N7/graph.json","events_json":"https://pith.science/api/pith-number/4KVPXCPAKQ6WUJUTEOVTUMG5N7/events.json","paper":"https://pith.science/paper/4KVPXCPA"},"agent_actions":{"view_html":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7","download_json":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7.json","view_paper":"https://pith.science/paper/4KVPXCPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04360&json=true","fetch_graph":"https://pith.science/api/pith-number/4KVPXCPAKQ6WUJUTEOVTUMG5N7/graph.json","fetch_events":"https://pith.science/api/pith-number/4KVPXCPAKQ6WUJUTEOVTUMG5N7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7/action/storage_attestation","attest_author":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7/action/author_attestation","sign_citation":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7/action/citation_signature","submit_replication":"https://pith.science/pith/4KVPXCPAKQ6WUJUTEOVTUMG5N7/action/replication_record"}},"created_at":"2026-06-04T01:09:05.198025+00:00","updated_at":"2026-06-04T01:09:05.198025+00:00"}