{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GKG63OLNBQFH7EBAR2KRPYM2SL","short_pith_number":"pith:GKG63OLN","schema_version":"1.0","canonical_sha256":"328dedb96d0c0a7f90208e9517e19a92d8718695a5c24437cacce37ba10bb279","source":{"kind":"arxiv","id":"2608.05651","version":1},"attestation_state":"computed","paper":{"title":"Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Guanzhi Deng, Haibo Wang, Haochen Luo, Junlan Feng, Lei Li, Qi Liu, Sichun Luo, Yi Huang, Zefa Hu","submitted_at":"2026-08-06T06:48:08Z","abstract_excerpt":"Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget. However, existing approaches typically allocate models at the level of individual queries or mutation steps, overlooking that evolutionary search is \\textit{stateful}: each generated candidate changes the population from which subsequent mutations are produced.\n  We empirically analyze LLM-driven evolutionary trajectories and "},"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":"2608.05651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T06:48:08Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"8056a3e4e67b35aabfc324cddf8799e3473bf7447c594d49c270c75138fd2cdd","abstract_canon_sha256":"7bf9830f5ea7d5b8ff84a8c41b05848e2dcb0438300d79b16f1577d36f5acee4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:17.554825Z","signature_b64":"H6I8Q/3yqtFNyI2w2sckPnfjUwoCizbCoW8N0Vc6UkkyoiplWF3lldLjkeSwzI2NADjsMmfOLlY1qnsvQuAZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"328dedb96d0c0a7f90208e9517e19a92d8718695a5c24437cacce37ba10bb279","last_reissued_at":"2026-08-07T00:52:17.553291Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:17.553291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Guanzhi Deng, Haibo Wang, Haochen Luo, Junlan Feng, Lei Li, Qi Liu, Sichun Luo, Yi Huang, Zefa Hu","submitted_at":"2026-08-06T06:48:08Z","abstract_excerpt":"Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget. However, existing approaches typically allocate models at the level of individual queries or mutation steps, overlooking that evolutionary search is \\textit{stateful}: each generated candidate changes the population from which subsequent mutations are produced.\n  We empirically analyze LLM-driven evolutionary trajectories and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05651","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/2608.05651/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":"2608.05651","created_at":"2026-08-07T00:52:17.554849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05651v1","created_at":"2026-08-07T00:52:17.554849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05651","created_at":"2026-08-07T00:52:17.554849+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKG63OLNBQFH","created_at":"2026-08-07T00:52:17.554849+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKG63OLNBQFH7EBA","created_at":"2026-08-07T00:52:17.554849+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKG63OLN","created_at":"2026-08-07T00:52:17.554849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10694","citing_title":"Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL","json":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL.json","graph_json":"https://pith.science/api/pith-number/GKG63OLNBQFH7EBAR2KRPYM2SL/graph.json","events_json":"https://pith.science/api/pith-number/GKG63OLNBQFH7EBAR2KRPYM2SL/events.json","paper":"https://pith.science/paper/GKG63OLN"},"agent_actions":{"view_html":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL","download_json":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL.json","view_paper":"https://pith.science/paper/GKG63OLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05651&json=true","fetch_graph":"https://pith.science/api/pith-number/GKG63OLNBQFH7EBAR2KRPYM2SL/graph.json","fetch_events":"https://pith.science/api/pith-number/GKG63OLNBQFH7EBAR2KRPYM2SL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL/action/storage_attestation","attest_author":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL/action/author_attestation","sign_citation":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL/action/citation_signature","submit_replication":"https://pith.science/pith/GKG63OLNBQFH7EBAR2KRPYM2SL/action/replication_record"}},"created_at":"2026-08-07T00:52:17.554849+00:00","updated_at":"2026-08-07T00:52:17.554849+00:00"}