{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HLEN25SLG3SA6T54K57ZKEZYNT","short_pith_number":"pith:HLEN25SL","schema_version":"1.0","canonical_sha256":"3ac8dd764b36e40f4fbc577f9513386cfac2084d793c757c2cd944b92c860640","source":{"kind":"arxiv","id":"2503.06512","version":2},"attestation_state":"computed","paper":{"title":"LLM-Feynman: Leveraging Large Language Models for Universal Scientific Formula and Theory Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Chongyi Ling, Chunjin Ren, Jinlan Wang, Minggang Ju, Qionghua Zhou, Zhilong Song","submitted_at":"2025-03-09T08:34:51Z","abstract_excerpt":"Distilling underlying principles from data has historically driven scientific breakthroughs. However, conventional data-driven machine learning often produces complex models that lack interpretability and generalization due to insufficient domain expertise. Here, we present LLM-Feynman, a novel framework that leverages large language models (LLMs) alongside systematic optimization to derive concise, interpretable formulas from data and domain knowledge. Our method integrates automated feature engineering, LLM-guided symbolic regression with self-evaluation, and Monte Carlo tree search to enhan"},"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":"2503.06512","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-03-09T08:34:51Z","cross_cats_sorted":[],"title_canon_sha256":"5efef0717740f1b2bd0834bf65aa48a9f94e093613a2562f9d0df980907da17b","abstract_canon_sha256":"3a24ca7f13117912cb79182c5be3dac7bc541076fbb1f8f3df36795e17fa203d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:10.337908Z","signature_b64":"IAo6MMpFb3ABQLvnWMKV07YzmjkgDqnn+pNMoZYMJ3FHaatw2tSkn3Mq4cU7ggDqfki2FoVdEPkByBXrTi37Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac8dd764b36e40f4fbc577f9513386cfac2084d793c757c2cd944b92c860640","last_reissued_at":"2026-07-05T11:43:10.337453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:10.337453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Feynman: Leveraging Large Language Models for Universal Scientific Formula and Theory Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Chongyi Ling, Chunjin Ren, Jinlan Wang, Minggang Ju, Qionghua Zhou, Zhilong Song","submitted_at":"2025-03-09T08:34:51Z","abstract_excerpt":"Distilling underlying principles from data has historically driven scientific breakthroughs. However, conventional data-driven machine learning often produces complex models that lack interpretability and generalization due to insufficient domain expertise. Here, we present LLM-Feynman, a novel framework that leverages large language models (LLMs) alongside systematic optimization to derive concise, interpretable formulas from data and domain knowledge. Our method integrates automated feature engineering, LLM-guided symbolic regression with self-evaluation, and Monte Carlo tree search to enhan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06512","kind":"arxiv","version":2},"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/2503.06512/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":"2503.06512","created_at":"2026-07-05T11:43:10.337508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06512v2","created_at":"2026-07-05T11:43:10.337508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06512","created_at":"2026-07-05T11:43:10.337508+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLEN25SLG3SA","created_at":"2026-07-05T11:43:10.337508+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLEN25SLG3SA6T54","created_at":"2026-07-05T11:43:10.337508+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLEN25SL","created_at":"2026-07-05T11:43:10.337508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":274,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19789","citing_title":"From Data to Theory: Autonomous Large Language Model Agents for Materials Science","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00149","citing_title":"Towards Verifiable and Self-Correcting AI Physicists for Quantum Many-Body Simulations","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13131","citing_title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT","json":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT.json","graph_json":"https://pith.science/api/pith-number/HLEN25SLG3SA6T54K57ZKEZYNT/graph.json","events_json":"https://pith.science/api/pith-number/HLEN25SLG3SA6T54K57ZKEZYNT/events.json","paper":"https://pith.science/paper/HLEN25SL"},"agent_actions":{"view_html":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT","download_json":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT.json","view_paper":"https://pith.science/paper/HLEN25SL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06512&json=true","fetch_graph":"https://pith.science/api/pith-number/HLEN25SLG3SA6T54K57ZKEZYNT/graph.json","fetch_events":"https://pith.science/api/pith-number/HLEN25SLG3SA6T54K57ZKEZYNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT/action/storage_attestation","attest_author":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT/action/author_attestation","sign_citation":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT/action/citation_signature","submit_replication":"https://pith.science/pith/HLEN25SLG3SA6T54K57ZKEZYNT/action/replication_record"}},"created_at":"2026-07-05T11:43:10.337508+00:00","updated_at":"2026-07-05T11:43:10.337508+00:00"}