{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FL6E2B4SPLDRP2YYOJQNDF43OA","short_pith_number":"pith:FL6E2B4S","schema_version":"1.0","canonical_sha256":"2afc4d07927ac717eb187260d1979b701bebab8249ff3f4294e1207e18a70c2b","source":{"kind":"arxiv","id":"2506.04282","version":1},"attestation_state":"computed","paper":{"title":"DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boxiao Wang, Jian Cheng, Kai Li, Runxiang Wang, Yifan Zhang","submitted_at":"2025-06-04T04:52:34Z","abstract_excerpt":"Symbolic regression is a fundamental tool for discovering interpretable mathematical expressions from data, with broad applications across scientific and engineering domains. Recently, large language models (LLMs) have demonstrated strong performance in this task, leveraging embedded scientific priors and reasoning capabilities to surpass traditional methods. However, existing LLM-based approaches, such as LLM-SR, often over-rely on internal priors, lacking explicit data understanding and systematic reflection during equation generation. To address these limitations, we propose DrSR (Dual Reas"},"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":"2506.04282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T04:52:34Z","cross_cats_sorted":[],"title_canon_sha256":"8e0021d99f49d37f311c9d0b868d956909d4e334ecd3726e6f57b4683ed3543d","abstract_canon_sha256":"3ec464b6b111656f6b42deea1886c56f46cef9a71f376de46165c1201145f90c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:11.644577Z","signature_b64":"zW9UIApYMsPZ8J9/i5aOgCyHiY2Ip68EP1jKdlYwlkaJqyQUd1oaVSjyhlxfKCYk5suOWJO6edzVVAYEqNQjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2afc4d07927ac717eb187260d1979b701bebab8249ff3f4294e1207e18a70c2b","last_reissued_at":"2026-07-05T11:16:11.644068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:11.644068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boxiao Wang, Jian Cheng, Kai Li, Runxiang Wang, Yifan Zhang","submitted_at":"2025-06-04T04:52:34Z","abstract_excerpt":"Symbolic regression is a fundamental tool for discovering interpretable mathematical expressions from data, with broad applications across scientific and engineering domains. Recently, large language models (LLMs) have demonstrated strong performance in this task, leveraging embedded scientific priors and reasoning capabilities to surpass traditional methods. However, existing LLM-based approaches, such as LLM-SR, often over-rely on internal priors, lacking explicit data understanding and systematic reflection during equation generation. To address these limitations, we propose DrSR (Dual Reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04282","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/2506.04282/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":"2506.04282","created_at":"2026-07-05T11:16:11.644134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04282v1","created_at":"2026-07-05T11:16:11.644134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04282","created_at":"2026-07-05T11:16:11.644134+00:00"},{"alias_kind":"pith_short_12","alias_value":"FL6E2B4SPLDR","created_at":"2026-07-05T11:16:11.644134+00:00"},{"alias_kind":"pith_short_16","alias_value":"FL6E2B4SPLDRP2YY","created_at":"2026-07-05T11:16:11.644134+00:00"},{"alias_kind":"pith_short_8","alias_value":"FL6E2B4S","created_at":"2026-07-05T11:16:11.644134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07704","citing_title":"FunctionEvolve: Structure-Guided Symbolic Regression with LLMs","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23754","citing_title":"LLM-driven design of physics-constrained constitutive models: two agents are better than one","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06998","citing_title":"Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17790","citing_title":"STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06123","citing_title":"Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06998","citing_title":"Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA","json":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA.json","graph_json":"https://pith.science/api/pith-number/FL6E2B4SPLDRP2YYOJQNDF43OA/graph.json","events_json":"https://pith.science/api/pith-number/FL6E2B4SPLDRP2YYOJQNDF43OA/events.json","paper":"https://pith.science/paper/FL6E2B4S"},"agent_actions":{"view_html":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA","download_json":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA.json","view_paper":"https://pith.science/paper/FL6E2B4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04282&json=true","fetch_graph":"https://pith.science/api/pith-number/FL6E2B4SPLDRP2YYOJQNDF43OA/graph.json","fetch_events":"https://pith.science/api/pith-number/FL6E2B4SPLDRP2YYOJQNDF43OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA/action/storage_attestation","attest_author":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA/action/author_attestation","sign_citation":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA/action/citation_signature","submit_replication":"https://pith.science/pith/FL6E2B4SPLDRP2YYOJQNDF43OA/action/replication_record"}},"created_at":"2026-07-05T11:16:11.644134+00:00","updated_at":"2026-07-05T11:16:11.644134+00:00"}