{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SO7I7LWVPUA5V5AIQQJCWIOTCW","short_pith_number":"pith:SO7I7LWV","schema_version":"1.0","canonical_sha256":"93be8faed57d01daf40884122b21d31584ba66eaa2146230e8f4f7d4618bc851","source":{"kind":"arxiv","id":"2602.10233","version":2},"attestation_state":"computed","paper":{"title":"ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.CA","math.MG","math.OC"],"primary_cat":"cs.NE","authors_text":"Alexey Kravatskiy, Ivan Oseledets, Valentin Khrulkov","submitted_at":"2026-02-10T19:23:13Z","abstract_excerpt":"LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evolve a monolithic program that directly outputs a candidate solution. We present ImprovEvolve, an algorithmic alternative that drastically reduces cognitive load on the LLM. Instead of prompting the model for an end-to-end optimizer, we evolve a program with three specialized operators of initialization, local improvement, and perturbation. We then approach the optimum by iterati"},"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":"2602.10233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-02-10T19:23:13Z","cross_cats_sorted":["cs.AI","math.CA","math.MG","math.OC"],"title_canon_sha256":"e391c51e985a4a7fbcdc0da8d9e093d516f1a008328083f9478a6e6b3fb8b00c","abstract_canon_sha256":"580e09688682438fd911c2553bebf5522d1ffc08c28a28679ac38b406b0b06be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:09.062233Z","signature_b64":"snrffXOI50TjXwHdZVGCF+wlXZ54nZOX/u/VhZJDWC7Ig6opVm9kxOv7nYM1RD6EnPyICRATSinvs6gPhWI6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93be8faed57d01daf40884122b21d31584ba66eaa2146230e8f4f7d4618bc851","last_reissued_at":"2026-06-30T00:15:09.061843Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:09.061843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.CA","math.MG","math.OC"],"primary_cat":"cs.NE","authors_text":"Alexey Kravatskiy, Ivan Oseledets, Valentin Khrulkov","submitted_at":"2026-02-10T19:23:13Z","abstract_excerpt":"LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evolve a monolithic program that directly outputs a candidate solution. We present ImprovEvolve, an algorithmic alternative that drastically reduces cognitive load on the LLM. Instead of prompting the model for an end-to-end optimizer, we evolve a program with three specialized operators of initialization, local improvement, and perturbation. We then approach the optimum by iterati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10233","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/2602.10233/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":"2602.10233","created_at":"2026-06-30T00:15:09.061893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10233v2","created_at":"2026-06-30T00:15:09.061893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10233","created_at":"2026-06-30T00:15:09.061893+00:00"},{"alias_kind":"pith_short_12","alias_value":"SO7I7LWVPUA5","created_at":"2026-06-30T00:15:09.061893+00:00"},{"alias_kind":"pith_short_16","alias_value":"SO7I7LWVPUA5V5AI","created_at":"2026-06-30T00:15:09.061893+00:00"},{"alias_kind":"pith_short_8","alias_value":"SO7I7LWV","created_at":"2026-06-30T00:15:09.061893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15334","citing_title":"From I/O to Code with Discovery Agent","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW","json":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW.json","graph_json":"https://pith.science/api/pith-number/SO7I7LWVPUA5V5AIQQJCWIOTCW/graph.json","events_json":"https://pith.science/api/pith-number/SO7I7LWVPUA5V5AIQQJCWIOTCW/events.json","paper":"https://pith.science/paper/SO7I7LWV"},"agent_actions":{"view_html":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW","download_json":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW.json","view_paper":"https://pith.science/paper/SO7I7LWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10233&json=true","fetch_graph":"https://pith.science/api/pith-number/SO7I7LWVPUA5V5AIQQJCWIOTCW/graph.json","fetch_events":"https://pith.science/api/pith-number/SO7I7LWVPUA5V5AIQQJCWIOTCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW/action/storage_attestation","attest_author":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW/action/author_attestation","sign_citation":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW/action/citation_signature","submit_replication":"https://pith.science/pith/SO7I7LWVPUA5V5AIQQJCWIOTCW/action/replication_record"}},"created_at":"2026-06-30T00:15:09.061893+00:00","updated_at":"2026-06-30T00:15:09.061893+00:00"}