{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YOWAHYO4TSDDPJQFL7QXL5OR27","short_pith_number":"pith:YOWAHYO4","schema_version":"1.0","canonical_sha256":"c3ac03e1dc9c8637a6055fe175f5d1d7d2a952987d36d517de08f94eb03f5a98","source":{"kind":"arxiv","id":"2607.27389","version":1},"attestation_state":"computed","paper":{"title":"FunL2O: LLM-Guided Feature Function Design for Learning to Optimize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingheng Li, Bistra Dilkina, Dzung T. Phan, Jayant Kalagnanam, Junyang Cai, Yupeng Zhang","submitted_at":"2026-07-29T18:52:44Z","abstract_excerpt":"Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other forms of solver guidance. A critical yet largely overlooked component of these pipelines is the feature function that maps problem instances to inputs for machine learning models. Existing L2O methods typically rely on hand-crafted features, making representation design manual and largely fixed across domains. We introduce FunL2O, the first unified framework for automating feature design through LLM-driven program evolution for L2O. In a FunSea"},"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":"2607.27389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T18:52:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f631ae455d3e7c3e3472853e34dd849fb456829a37d7624ead80068736bb9037","abstract_canon_sha256":"e3132d03c69ad6653b91fd4d9a55f6be0e74eac28a0885f61a9cb3132e14dc6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3ac03e1dc9c8637a6055fe175f5d1d7d2a952987d36d517de08f94eb03f5a98","last_reissued_at":"2026-07-31T00:10:52.224514Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:52.224514Z"},"graph_snapshot":{"paper":{"title":"FunL2O: LLM-Guided Feature Function Design for Learning to Optimize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingheng Li, Bistra Dilkina, Dzung T. Phan, Jayant Kalagnanam, Junyang Cai, Yupeng Zhang","submitted_at":"2026-07-29T18:52:44Z","abstract_excerpt":"Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other forms of solver guidance. A critical yet largely overlooked component of these pipelines is the feature function that maps problem instances to inputs for machine learning models. Existing L2O methods typically rely on hand-crafted features, making representation design manual and largely fixed across domains. We introduce FunL2O, the first unified framework for automating feature design through LLM-driven program evolution for L2O. In a FunSea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27389","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/2607.27389/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":"2607.27389","created_at":"2026-07-31T00:10:52.226795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27389v1","created_at":"2026-07-31T00:10:52.226795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27389","created_at":"2026-07-31T00:10:52.226795+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOWAHYO4TSDD","created_at":"2026-07-31T00:10:52.226795+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOWAHYO4TSDDPJQF","created_at":"2026-07-31T00:10:52.226795+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOWAHYO4","created_at":"2026-07-31T00:10:52.226795+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/YOWAHYO4TSDDPJQFL7QXL5OR27","json":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27.json","graph_json":"https://pith.science/api/pith-number/YOWAHYO4TSDDPJQFL7QXL5OR27/graph.json","events_json":"https://pith.science/api/pith-number/YOWAHYO4TSDDPJQFL7QXL5OR27/events.json","paper":"https://pith.science/paper/YOWAHYO4"},"agent_actions":{"view_html":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27","download_json":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27.json","view_paper":"https://pith.science/paper/YOWAHYO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27389&json=true","fetch_graph":"https://pith.science/api/pith-number/YOWAHYO4TSDDPJQFL7QXL5OR27/graph.json","fetch_events":"https://pith.science/api/pith-number/YOWAHYO4TSDDPJQFL7QXL5OR27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27/action/storage_attestation","attest_author":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27/action/author_attestation","sign_citation":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27/action/citation_signature","submit_replication":"https://pith.science/pith/YOWAHYO4TSDDPJQFL7QXL5OR27/action/replication_record"}},"created_at":"2026-07-31T00:10:52.226795+00:00","updated_at":"2026-07-31T00:10:52.226795+00:00"}