{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WWLG2PQFQFAVGA3YQEG7OZ2BA","short_pith_number":"pith:3WWLG2PQ","schema_version":"1.0","canonical_sha256":"ddacb369f02c0a0a981bc4086fbb3a08216c1ba885649a4584e80217517aa6b0","source":{"kind":"arxiv","id":"2505.12285","version":1},"attestation_state":"computed","paper":{"title":"CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jianping Wang, Kui Wu, Wei-Bin Lee, WeiWei Wu, Ziyao Huang","submitted_at":"2025-05-18T07:48:47Z","abstract_excerpt":"Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed evolutionary search frameworks, can autonomously discover high-performing heuristics at a fraction of the traditional cost. However, existing approaches predominantly rely on verbal guidance, i.e., manipulating the prompt generation process, to steer the evolution of heuristics, without adapting the underlying LLM. We propose a hybrid framework that combines verba"},"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":"2505.12285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-05-18T07:48:47Z","cross_cats_sorted":[],"title_canon_sha256":"c803c5e7d647bc38a2ac4cfdc12732d762e8db68ac27df74efd6ae873a18171d","abstract_canon_sha256":"cde6e083c4ea9c68573464e3e6641d4802e4186350a6fca27cb00a1eac6eb793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:01.591651Z","signature_b64":"0hgf3L94XNt6qwQJnC2WTmAKjjVxvsEg9Bw/AuaoknDTu3S+D+aqqc8Gwe3ASpaC6eUPGJkkDj29ea5j8co5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddacb369f02c0a0a981bc4086fbb3a08216c1ba885649a4584e80217517aa6b0","last_reissued_at":"2026-07-05T11:05:01.591100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:01.591100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jianping Wang, Kui Wu, Wei-Bin Lee, WeiWei Wu, Ziyao Huang","submitted_at":"2025-05-18T07:48:47Z","abstract_excerpt":"Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed evolutionary search frameworks, can autonomously discover high-performing heuristics at a fraction of the traditional cost. However, existing approaches predominantly rely on verbal guidance, i.e., manipulating the prompt generation process, to steer the evolution of heuristics, without adapting the underlying LLM. We propose a hybrid framework that combines verba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12285","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/2505.12285/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":"2505.12285","created_at":"2026-07-05T11:05:01.591163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12285v1","created_at":"2026-07-05T11:05:01.591163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12285","created_at":"2026-07-05T11:05:01.591163+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WWLG2PQFQFA","created_at":"2026-07-05T11:05:01.591163+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WWLG2PQFQFAVGA3","created_at":"2026-07-05T11:05:01.591163+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WWLG2PQ","created_at":"2026-07-05T11:05:01.591163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00604","citing_title":"Vehicle Routing Problem Meets Large Language Models: An Overview and Perspectives","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2507.10614","citing_title":"Fine-tuning Large Language Model for Automated Algorithm Design","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20849","citing_title":"Large Language Models for Operations Research: A Comprehensive Survey","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27176","citing_title":"Glia: A Human-Inspired AI for Automated Systems Design and Optimization","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA","json":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA.json","graph_json":"https://pith.science/api/pith-number/3WWLG2PQFQFAVGA3YQEG7OZ2BA/graph.json","events_json":"https://pith.science/api/pith-number/3WWLG2PQFQFAVGA3YQEG7OZ2BA/events.json","paper":"https://pith.science/paper/3WWLG2PQ"},"agent_actions":{"view_html":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA","download_json":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA.json","view_paper":"https://pith.science/paper/3WWLG2PQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12285&json=true","fetch_graph":"https://pith.science/api/pith-number/3WWLG2PQFQFAVGA3YQEG7OZ2BA/graph.json","fetch_events":"https://pith.science/api/pith-number/3WWLG2PQFQFAVGA3YQEG7OZ2BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA/action/storage_attestation","attest_author":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA/action/author_attestation","sign_citation":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA/action/citation_signature","submit_replication":"https://pith.science/pith/3WWLG2PQFQFAVGA3YQEG7OZ2BA/action/replication_record"}},"created_at":"2026-07-05T11:05:01.591163+00:00","updated_at":"2026-07-05T11:05:01.591163+00:00"}