{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OEO52C5ZYYWHT7OIIRZDEA3B53","short_pith_number":"pith:OEO52C5Z","schema_version":"1.0","canonical_sha256":"711ddd0bb9c62c79fdc84472320361eef4e082af023bffdeee55d0bf74210d61","source":{"kind":"arxiv","id":"2505.07956","version":1},"attestation_state":"computed","paper":{"title":"Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","cs.SC"],"primary_cat":"cs.LG","authors_text":"Fabian Ruehle, James Halverson, Kit Fraser-Taliente, Thomas R. Harvey","submitted_at":"2025-05-12T18:00:41Z","abstract_excerpt":"We present a novel approach to symbolic regression using vision-capable large language models (LLMs) and the ideas behind Google DeepMind's Funsearch. The LLM is given a plot of a univariate function and tasked with proposing an ansatz for that function. The free parameters of the ansatz are fitted using standard numerical optimisers, and a collection of such ans\\\"atze make up the population of a genetic algorithm. Unlike other symbolic regression techniques, our method does not require the specification of a set of functions to be used in regression, but with appropriate prompt engineering, w"},"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":"2505.07956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T18:00:41Z","cross_cats_sorted":["cs.NE","cs.SC"],"title_canon_sha256":"4805947eccb7d5fee2b5ac1bc1470164dd43e734b17facd7d785939f95eb898b","abstract_canon_sha256":"e2097451fa4fa3572f72a320a19f50ac0c439d3d0e0eac2c1cfaf8a366e81d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:24.834154Z","signature_b64":"+WTxLRSGOIo5+ANfEcN18BO70HAtQUy91PgmHac5XTB0aZEPEj+Vs9/nH8Xic0cfT8DGTwiGZAHo5iPOHtjgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"711ddd0bb9c62c79fdc84472320361eef4e082af023bffdeee55d0bf74210d61","last_reissued_at":"2026-07-05T11:05:24.833685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:24.833685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","cs.SC"],"primary_cat":"cs.LG","authors_text":"Fabian Ruehle, James Halverson, Kit Fraser-Taliente, Thomas R. Harvey","submitted_at":"2025-05-12T18:00:41Z","abstract_excerpt":"We present a novel approach to symbolic regression using vision-capable large language models (LLMs) and the ideas behind Google DeepMind's Funsearch. The LLM is given a plot of a univariate function and tasked with proposing an ansatz for that function. The free parameters of the ansatz are fitted using standard numerical optimisers, and a collection of such ans\\\"atze make up the population of a genetic algorithm. Unlike other symbolic regression techniques, our method does not require the specification of a set of functions to be used in regression, but with appropriate prompt engineering, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07956","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/2505.07956/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":"2505.07956","created_at":"2026-07-05T11:05:24.833743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07956v1","created_at":"2026-07-05T11:05:24.833743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07956","created_at":"2026-07-05T11:05:24.833743+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEO52C5ZYYWH","created_at":"2026-07-05T11:05:24.833743+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEO52C5ZYYWHT7OI","created_at":"2026-07-05T11:05:24.833743+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEO52C5Z","created_at":"2026-07-05T11:05:24.833743+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/OEO52C5ZYYWHT7OIIRZDEA3B53","json":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53.json","graph_json":"https://pith.science/api/pith-number/OEO52C5ZYYWHT7OIIRZDEA3B53/graph.json","events_json":"https://pith.science/api/pith-number/OEO52C5ZYYWHT7OIIRZDEA3B53/events.json","paper":"https://pith.science/paper/OEO52C5Z"},"agent_actions":{"view_html":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53","download_json":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53.json","view_paper":"https://pith.science/paper/OEO52C5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07956&json=true","fetch_graph":"https://pith.science/api/pith-number/OEO52C5ZYYWHT7OIIRZDEA3B53/graph.json","fetch_events":"https://pith.science/api/pith-number/OEO52C5ZYYWHT7OIIRZDEA3B53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53/action/storage_attestation","attest_author":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53/action/author_attestation","sign_citation":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53/action/citation_signature","submit_replication":"https://pith.science/pith/OEO52C5ZYYWHT7OIIRZDEA3B53/action/replication_record"}},"created_at":"2026-07-05T11:05:24.833743+00:00","updated_at":"2026-07-05T11:05:24.833743+00:00"}