{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NEWAQM2R7NMOGIMVEENLU2ZWIO","short_pith_number":"pith:NEWAQM2R","schema_version":"1.0","canonical_sha256":"692c083351fb58e32195211aba6b3643b3f8b492e2af274b88594b22e1e525b2","source":{"kind":"arxiv","id":"2502.11607","version":2},"attestation_state":"computed","paper":{"title":"GraphThought: Graph Combinatorial Optimization with Thought Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Jin, Changhong Lu, Chuyun Shen, Haosheng Chen, Junjie Sheng, Lifeng Guo, Wenhao Li, Xiangfeng Wang, Zixiao Huang","submitted_at":"2025-02-17T09:50:41Z","abstract_excerpt":"Graph combinatorial optimization (GCO) problems are central to domains like logistics and bioinformatics. While traditional solvers dominate, large language models (LLMs) offer new possibilities for structured reasoning, yet struggle with complex GCO tasks requiring rigorous combinatorial analysis and multi-step deduction, often producing hallucinated steps. We first formalize the Optimal Thoughts Design (OTD) problem, which provides a structured guidance for producing high-quality intermediate reasoning steps. Building on this formulation, we introduce GraphThought, a novel framework that gen"},"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":"2502.11607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T09:50:41Z","cross_cats_sorted":[],"title_canon_sha256":"99a7aa7373fd3838c2dbd72f41ee420f1903a38c2e7685aa3b4a38f7b716371d","abstract_canon_sha256":"0efa6711e41cce433903941442d3e036613eafdeb598412ab15e135ce706277d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:09.357558Z","signature_b64":"Pi+GfKM74+eUUuaG7kEkFQlCM/dNiG4JOKJjrLYBJxpDH84ZSWMeHKKz0VNDVSOA1qcoGn9ydvT4iTcJ/0DOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"692c083351fb58e32195211aba6b3643b3f8b492e2af274b88594b22e1e525b2","last_reissued_at":"2026-07-05T11:20:09.356932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:09.356932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphThought: Graph Combinatorial Optimization with Thought Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Jin, Changhong Lu, Chuyun Shen, Haosheng Chen, Junjie Sheng, Lifeng Guo, Wenhao Li, Xiangfeng Wang, Zixiao Huang","submitted_at":"2025-02-17T09:50:41Z","abstract_excerpt":"Graph combinatorial optimization (GCO) problems are central to domains like logistics and bioinformatics. While traditional solvers dominate, large language models (LLMs) offer new possibilities for structured reasoning, yet struggle with complex GCO tasks requiring rigorous combinatorial analysis and multi-step deduction, often producing hallucinated steps. We first formalize the Optimal Thoughts Design (OTD) problem, which provides a structured guidance for producing high-quality intermediate reasoning steps. Building on this formulation, we introduce GraphThought, a novel framework that gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11607","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/2502.11607/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":"2502.11607","created_at":"2026-07-05T11:20:09.357023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11607v2","created_at":"2026-07-05T11:20:09.357023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11607","created_at":"2026-07-05T11:20:09.357023+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEWAQM2R7NMO","created_at":"2026-07-05T11:20:09.357023+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEWAQM2R7NMOGIMV","created_at":"2026-07-05T11:20:09.357023+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEWAQM2R","created_at":"2026-07-05T11:20:09.357023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06865","citing_title":"Are Large Language Models Suitable for Graph Computation? Progress and Prospects","ref_index":198,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20849","citing_title":"Large Language Models for Operations Research: A Comprehensive Survey","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02188","citing_title":"Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01410","citing_title":"GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13221","citing_title":"An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO","json":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO.json","graph_json":"https://pith.science/api/pith-number/NEWAQM2R7NMOGIMVEENLU2ZWIO/graph.json","events_json":"https://pith.science/api/pith-number/NEWAQM2R7NMOGIMVEENLU2ZWIO/events.json","paper":"https://pith.science/paper/NEWAQM2R"},"agent_actions":{"view_html":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO","download_json":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO.json","view_paper":"https://pith.science/paper/NEWAQM2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11607&json=true","fetch_graph":"https://pith.science/api/pith-number/NEWAQM2R7NMOGIMVEENLU2ZWIO/graph.json","fetch_events":"https://pith.science/api/pith-number/NEWAQM2R7NMOGIMVEENLU2ZWIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO/action/storage_attestation","attest_author":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO/action/author_attestation","sign_citation":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO/action/citation_signature","submit_replication":"https://pith.science/pith/NEWAQM2R7NMOGIMVEENLU2ZWIO/action/replication_record"}},"created_at":"2026-07-05T11:20:09.357023+00:00","updated_at":"2026-07-05T11:20:09.357023+00:00"}