{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5SKZSC77ULA3XGMHKKWI4O63TN","short_pith_number":"pith:5SKZSC77","schema_version":"1.0","canonical_sha256":"ec95990bffa2c1bb998752ac8e3bdb9b6388645c0a6a491eef36c5640345950c","source":{"kind":"arxiv","id":"2409.09359","version":3},"attestation_state":"computed","paper":{"title":"Symbolic Regression with a Learned Concept Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SC"],"primary_cat":"cs.LG","authors_text":"Arya Grayeli, Atharva Sehgal, Miles Cranmer, Omar Costilla-Reyes, Swarat Chaudhuri","submitted_at":"2024-09-14T08:17:30Z","abstract_excerpt":"We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods by inducing a library of abstract textual concepts. Our algorithm, called LaSR, uses zero-shot queries to a large language model (LLM) to discover and evolve concepts occurring in known high-performing hypotheses. We discover new hypotheses using a mix of standard evolutionary steps and LLM-guided steps (obtained through zero-shot LLM queries) conditioned o"},"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":"2409.09359","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T08:17:30Z","cross_cats_sorted":["cs.AI","cs.NE","cs.SC"],"title_canon_sha256":"d0dbeead0d71c57a87e06a915d61521f6627d8acd7214d9b9beb8a8c2912e487","abstract_canon_sha256":"516299411f999c29a112d2a0463a4a69e20ef90fa5a3fece70ed158f414c5cf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:51.557487Z","signature_b64":"QIBw61oY/GJCEQGdS20sc14r7/n8ETkn2RwVdn5GN7hT+2y8euT/ohsKfAWtDaFcvGcvlcgekvEKmcNmzOEKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec95990bffa2c1bb998752ac8e3bdb9b6388645c0a6a491eef36c5640345950c","last_reissued_at":"2026-07-05T09:46:51.556929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:51.556929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Regression with a Learned Concept Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SC"],"primary_cat":"cs.LG","authors_text":"Arya Grayeli, Atharva Sehgal, Miles Cranmer, Omar Costilla-Reyes, Swarat Chaudhuri","submitted_at":"2024-09-14T08:17:30Z","abstract_excerpt":"We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods by inducing a library of abstract textual concepts. Our algorithm, called LaSR, uses zero-shot queries to a large language model (LLM) to discover and evolve concepts occurring in known high-performing hypotheses. We discover new hypotheses using a mix of standard evolutionary steps and LLM-guided steps (obtained through zero-shot LLM queries) conditioned o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09359","kind":"arxiv","version":3},"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/2409.09359/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":"2409.09359","created_at":"2026-07-05T09:46:51.556988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09359v3","created_at":"2026-07-05T09:46:51.556988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09359","created_at":"2026-07-05T09:46:51.556988+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SKZSC77ULA3","created_at":"2026-07-05T09:46:51.556988+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SKZSC77ULA3XGMH","created_at":"2026-07-05T09:46:51.556988+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SKZSC77","created_at":"2026-07-05T09:46:51.556988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07704","citing_title":"FunctionEvolve: Structure-Guided Symbolic Regression with LLMs","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2410.17448","citing_title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN","json":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN.json","graph_json":"https://pith.science/api/pith-number/5SKZSC77ULA3XGMHKKWI4O63TN/graph.json","events_json":"https://pith.science/api/pith-number/5SKZSC77ULA3XGMHKKWI4O63TN/events.json","paper":"https://pith.science/paper/5SKZSC77"},"agent_actions":{"view_html":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN","download_json":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN.json","view_paper":"https://pith.science/paper/5SKZSC77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09359&json=true","fetch_graph":"https://pith.science/api/pith-number/5SKZSC77ULA3XGMHKKWI4O63TN/graph.json","fetch_events":"https://pith.science/api/pith-number/5SKZSC77ULA3XGMHKKWI4O63TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN/action/storage_attestation","attest_author":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN/action/author_attestation","sign_citation":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN/action/citation_signature","submit_replication":"https://pith.science/pith/5SKZSC77ULA3XGMHKKWI4O63TN/action/replication_record"}},"created_at":"2026-07-05T09:46:51.556988+00:00","updated_at":"2026-07-05T09:46:51.556988+00:00"}