{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KAE2E6X6AOCVUUKEI6CNFZ2ICZ","short_pith_number":"pith:KAE2E6X6","schema_version":"1.0","canonical_sha256":"5009a27afe03855a51444784d2e74816444a9b3267212c9e8c48410cc8562a6b","source":{"kind":"arxiv","id":"2508.07932","version":1},"attestation_state":"computed","paper":{"title":"\\(X\\)-evolve: Solution space evolution powered by large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianmin Ji, Keyu Pan, Lu Zhang, Ruohan Li, Shuo Liu, Wuyang Zhang, Yanyong Zhang, Yi Zhai, Yu Zhang, Zhiqiang Wei","submitted_at":"2025-08-11T12:47:59Z","abstract_excerpt":"While combining large language models (LLMs) with evolutionary algorithms (EAs) shows promise for solving complex optimization problems, current approaches typically evolve individual solutions, often incurring high LLM call costs. We introduce \\(X\\)-evolve, a paradigm-shifting method that instead evolves solution spaces \\(X\\) (sets of individual solutions) - subsets of the overall search space \\(S\\). In \\(X\\)-evolve, LLMs generate tunable programs wherein certain code snippets, designated as parameters, define a tunable solution space. A score-based search algorithm then efficiently explores "},"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":"2508.07932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-11T12:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"11c65bd0cd45fee8b1c04cd3d25acdb9495f882d3a67be64e57089441cd0fc4c","abstract_canon_sha256":"cc5fa0b9a25aec33d5c72ad03d1e9f5f032ae86863d5503694d5d70602325e8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:05.087350Z","signature_b64":"XAK82LoJVcrZA7aoHUar+2B0o2N7+IzfXOW90mfBbetoGMOXBp2+psOyAshVm6xcfMCtYHBWV3EPfKkeiks2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5009a27afe03855a51444784d2e74816444a9b3267212c9e8c48410cc8562a6b","last_reissued_at":"2026-07-05T11:52:05.086666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:05.086666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\\(X\\)-evolve: Solution space evolution powered by large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianmin Ji, Keyu Pan, Lu Zhang, Ruohan Li, Shuo Liu, Wuyang Zhang, Yanyong Zhang, Yi Zhai, Yu Zhang, Zhiqiang Wei","submitted_at":"2025-08-11T12:47:59Z","abstract_excerpt":"While combining large language models (LLMs) with evolutionary algorithms (EAs) shows promise for solving complex optimization problems, current approaches typically evolve individual solutions, often incurring high LLM call costs. We introduce \\(X\\)-evolve, a paradigm-shifting method that instead evolves solution spaces \\(X\\) (sets of individual solutions) - subsets of the overall search space \\(S\\). In \\(X\\)-evolve, LLMs generate tunable programs wherein certain code snippets, designated as parameters, define a tunable solution space. A score-based search algorithm then efficiently explores "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07932","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/2508.07932/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":"2508.07932","created_at":"2026-07-05T11:52:05.086758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07932v1","created_at":"2026-07-05T11:52:05.086758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07932","created_at":"2026-07-05T11:52:05.086758+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAE2E6X6AOCV","created_at":"2026-07-05T11:52:05.086758+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAE2E6X6AOCVUUKE","created_at":"2026-07-05T11:52:05.086758+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAE2E6X6","created_at":"2026-07-05T11:52:05.086758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12194","citing_title":"Beating Product Constructions for Linear Equations Over Finite Fields","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20086","citing_title":"What Do Evolutionary Coding Agents Evolve?","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27176","citing_title":"Glia: A Human-Inspired AI for Automated Systems Design and Optimization","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ","json":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ.json","graph_json":"https://pith.science/api/pith-number/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/graph.json","events_json":"https://pith.science/api/pith-number/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/events.json","paper":"https://pith.science/paper/KAE2E6X6"},"agent_actions":{"view_html":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ","download_json":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ.json","view_paper":"https://pith.science/paper/KAE2E6X6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07932&json=true","fetch_graph":"https://pith.science/api/pith-number/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/action/storage_attestation","attest_author":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/action/author_attestation","sign_citation":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/action/citation_signature","submit_replication":"https://pith.science/pith/KAE2E6X6AOCVUUKEI6CNFZ2ICZ/action/replication_record"}},"created_at":"2026-07-05T11:52:05.086758+00:00","updated_at":"2026-07-05T11:52:05.086758+00:00"}