{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5SE2N6NEA2X2EBYOZJMSPKTQHD","short_pith_number":"pith:5SE2N6NE","schema_version":"1.0","canonical_sha256":"ec89a6f9a406afa2070eca5927aa7038c72886bb2cd0e3c1bcef257b1e111d97","source":{"kind":"arxiv","id":"2505.20242","version":1},"attestation_state":"computed","paper":{"title":"RedAHD: Reduction-Based End-to-End Automatic Heuristic Design with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aida Riahifar, Hau Chan, Nathan Huynh, Nguyen Thach","submitted_at":"2025-05-26T17:21:16Z","abstract_excerpt":"Solving NP-hard combinatorial optimization problems (COPs) (e.g., traveling salesman problems (TSPs) and capacitated vehicle routing problems (CVRPs)) in practice traditionally involves handcrafting heuristics or specifying a search space for finding effective heuristics. The main challenges from these approaches, however, are the sheer amount of domain knowledge and implementation efforts required from human experts. Recently, significant progress has been made to address these challenges, particularly by using large language models (LLMs) to design heuristics within some predetermined genera"},"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":"2505.20242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:21:16Z","cross_cats_sorted":[],"title_canon_sha256":"c00e5bc5cf3ab5f4bdda5ac243ce48e7e94ab534667a7029c109f39c9dc378de","abstract_canon_sha256":"488e44f4e4a38bbc763d4cfb0fb046daf5131289a721a58627a774f51499c464"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:54.956883Z","signature_b64":"0vYGXNHipAWRud2I8y/aZCi0yEcqeEEJiSFJj3rQ2ggv6wgKD854iGjFQCqWmVvBZrHIlypVd1BJrRKpyeBJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec89a6f9a406afa2070eca5927aa7038c72886bb2cd0e3c1bcef257b1e111d97","last_reissued_at":"2026-07-05T11:09:54.956371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:54.956371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RedAHD: Reduction-Based End-to-End Automatic Heuristic Design with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aida Riahifar, Hau Chan, Nathan Huynh, Nguyen Thach","submitted_at":"2025-05-26T17:21:16Z","abstract_excerpt":"Solving NP-hard combinatorial optimization problems (COPs) (e.g., traveling salesman problems (TSPs) and capacitated vehicle routing problems (CVRPs)) in practice traditionally involves handcrafting heuristics or specifying a search space for finding effective heuristics. The main challenges from these approaches, however, are the sheer amount of domain knowledge and implementation efforts required from human experts. Recently, significant progress has been made to address these challenges, particularly by using large language models (LLMs) to design heuristics within some predetermined genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20242","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/2505.20242/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":"2505.20242","created_at":"2026-07-05T11:09:54.956439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20242v1","created_at":"2026-07-05T11:09:54.956439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20242","created_at":"2026-07-05T11:09:54.956439+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SE2N6NEA2X2","created_at":"2026-07-05T11:09:54.956439+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SE2N6NEA2X2EBYO","created_at":"2026-07-05T11:09:54.956439+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SE2N6NE","created_at":"2026-07-05T11:09:54.956439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01975","citing_title":"Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07872","citing_title":"PyVRP$^+$: LLM-Driven Metacognitive Heuristic Evolution for Hybrid Genetic Search in Vehicle Routing Problems","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD","json":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD.json","graph_json":"https://pith.science/api/pith-number/5SE2N6NEA2X2EBYOZJMSPKTQHD/graph.json","events_json":"https://pith.science/api/pith-number/5SE2N6NEA2X2EBYOZJMSPKTQHD/events.json","paper":"https://pith.science/paper/5SE2N6NE"},"agent_actions":{"view_html":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD","download_json":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD.json","view_paper":"https://pith.science/paper/5SE2N6NE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20242&json=true","fetch_graph":"https://pith.science/api/pith-number/5SE2N6NEA2X2EBYOZJMSPKTQHD/graph.json","fetch_events":"https://pith.science/api/pith-number/5SE2N6NEA2X2EBYOZJMSPKTQHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD/action/storage_attestation","attest_author":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD/action/author_attestation","sign_citation":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD/action/citation_signature","submit_replication":"https://pith.science/pith/5SE2N6NEA2X2EBYOZJMSPKTQHD/action/replication_record"}},"created_at":"2026-07-05T11:09:54.956439+00:00","updated_at":"2026-07-05T11:09:54.956439+00:00"}