{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QNE6M7I34RDIGWSDAJ4RA26EUA","short_pith_number":"pith:QNE6M7I3","canonical_record":{"source":{"id":"2605.14416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:05:22Z","cross_cats_sorted":[],"title_canon_sha256":"6d597269492c269738a83d7a698cb3dc078be69e23ea18195e50a3a9e7de21a8","abstract_canon_sha256":"f88afeb8bc5a0cdb2dba1101c43bc30c320a2c1924230ad1581bd593fb419220"},"schema_version":"1.0"},"canonical_sha256":"8349e67d1be446835a430279106bc4a00e55747bd9d161c83f34c204a91946be","source":{"kind":"arxiv","id":"2605.14416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14416","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14416v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14416","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"QNE6M7I34RDI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QNE6M7I34RDIGWSD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QNE6M7I3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QNE6M7I34RDIGWSDAJ4RA26EUA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:05:22Z","cross_cats_sorted":[],"title_canon_sha256":"6d597269492c269738a83d7a698cb3dc078be69e23ea18195e50a3a9e7de21a8","abstract_canon_sha256":"f88afeb8bc5a0cdb2dba1101c43bc30c320a2c1924230ad1581bd593fb419220"},"schema_version":"1.0"},"canonical_sha256":"8349e67d1be446835a430279106bc4a00e55747bd9d161c83f34c204a91946be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.301581Z","signature_b64":"yRahM4enr5OoJa6EznHW4zkF7D907Tjjt9SeWpIp0jCanOQqnQAQpYna7pgbixNIUIZi76CKuDGntdwFAXXXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8349e67d1be446835a430279106bc4a00e55747bd9d161c83f34c204a91946be","last_reissued_at":"2026-05-17T23:39:07.300744Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.300744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14416","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOsSskOmr0OZzA1FhSB6xwhf0GJhRPyr7e9EXJga5SpS0yeZDkLEj1MEpRW0bGoCh7cnYwjMkjvLjpAa2QjsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:27:03.455915Z"},"content_sha256":"ed230d4cb14c80ca1459277812ec17e29bb129362355d5a8c0713c6e1a330dd1","schema_version":"1.0","event_id":"sha256:ed230d4cb14c80ca1459277812ec17e29bb129362355d5a8c0713c6e1a330dd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QNE6M7I34RDIGWSDAJ4RA26EUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A framework embedding classical routing knowledge into RL achieves better solutions for diverse CVRP variants.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Hu, Liang Wang, Wen Wang, Xiangchen Wu, Xianping Tao","submitted_at":"2026-05-14T06:05:22Z","abstract_excerpt":"The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem with broad applications in logistics and transportation. Real-world CVRPs often involve diverse objectives and complex constraints, such as time windows or backhaul requirements, motivating the development of a unified solution framework. Recent reinforcement learning (RL) approaches have shown promise in combinatorial optimization, yet they rely on end-to-end learning and lack explicit problem-solving knowledge, limiting solution quality. In this paper, we propose a knowledge-embedded framework inspired by the Rou"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments show that this framework achieves superior solution quality compared with state-of-the-art learning-based methods, with a smaller gap to classical heuristics, demonstrating strong generalization across diverse CVRP variants.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Route-First Cluster-Second decomposition plus dynamic programming guidance will reliably mitigate partial observability and produce generalizable improvements without introducing new biases or overfitting to the tested CVRP variants.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A knowledge-embedded RL framework decomposes generalized CVRPs into route-first and cluster-second subproblems, using dynamic programming to guide the RL solver and a history-enhanced context module to handle partial observability, yielding better solutions than prior learning methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A framework embedding classical routing knowledge into RL achieves better solutions for diverse CVRP variants.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a5a7cbe3e560807b7369002c3a1c2b30d7bb080094d48e4791871fcccf748068"},"source":{"id":"2605.14416","kind":"arxiv","version":1},"verdict":{"id":"def30479-0570-414b-a712-e49a8c6ca532","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:06:16.113961Z","strongest_claim":"Extensive experiments show that this framework achieves superior solution quality compared with state-of-the-art learning-based methods, with a smaller gap to classical heuristics, demonstrating strong generalization across diverse CVRP variants.","one_line_summary":"A knowledge-embedded RL framework decomposes generalized CVRPs into route-first and cluster-second subproblems, using dynamic programming to guide the RL solver and a history-enhanced context module to handle partial observability, yielding better solutions than prior learning methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Route-First Cluster-Second decomposition plus dynamic programming guidance will reliably mitigate partial observability and produce generalizable improvements without introducing new biases or overfitting to the tested CVRP variants.","pith_extraction_headline":"A framework embedding classical routing knowledge into RL achieves better solutions for diverse CVRP variants."},"references":{"count":42,"sample":[{"doi":"","year":2024,"title":"Routefinder: Towards foundation models for vehicle routing problems","work_id":"65b94abc-7a2f-4393-bd62-6da2c721cfea","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Learn- ing to handle complex constraints for vehicle routing prob- lems.Advances in Neural Information Processing Sys- tems, 37:93479–93509,","work_id":"78783065-615f-42d4-8053-c9b54afe3327","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Learning to perform local rewriting for combinatorial opti- mization.Advances in neural information processing sys- tems, 32,","work_id":"6d943f93-f5a7-4c4c-bbd4-57d3c98f04b5","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Select and optimize: Learning to solve large-scale tsp instances","work_id":"87d25f8c-0301-493d-a781-843da427f284","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Learning 2-opt heuristics for the traveling salesman problem via deep re- inforcement learning","work_id":"f079835f-7cd1-4c98-8ea8-dc44846d6b10","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"8db56c4f55f4230dde80621239975e5ce37b6a865226bbef87ac9b758da6e7ac","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"},"verdict_id":"def30479-0570-414b-a712-e49a8c6ca532"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MpJCdwXncgv5EoS5wr7R88E7eTODEZLA7upK/e+0wptvss+By3FVy/69IN9QZqH0LQaju8mt8qWt6a2FIQ3mDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:27:03.457493Z"},"content_sha256":"ee9f2c0ee00943f41dbc08dbe7b4f649e27f8011175edf9751abc57bffcd45e5","schema_version":"1.0","event_id":"sha256:ee9f2c0ee00943f41dbc08dbe7b4f649e27f8011175edf9751abc57bffcd45e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNE6M7I34RDIGWSDAJ4RA26EUA/bundle.json","state_url":"https://pith.science/pith/QNE6M7I34RDIGWSDAJ4RA26EUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNE6M7I34RDIGWSDAJ4RA26EUA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T10:27:03Z","links":{"resolver":"https://pith.science/pith/QNE6M7I34RDIGWSDAJ4RA26EUA","bundle":"https://pith.science/pith/QNE6M7I34RDIGWSDAJ4RA26EUA/bundle.json","state":"https://pith.science/pith/QNE6M7I34RDIGWSDAJ4RA26EUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNE6M7I34RDIGWSDAJ4RA26EUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QNE6M7I34RDIGWSDAJ4RA26EUA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f88afeb8bc5a0cdb2dba1101c43bc30c320a2c1924230ad1581bd593fb419220","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:05:22Z","title_canon_sha256":"6d597269492c269738a83d7a698cb3dc078be69e23ea18195e50a3a9e7de21a8"},"schema_version":"1.0","source":{"id":"2605.14416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14416","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14416v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14416","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"QNE6M7I34RDI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QNE6M7I34RDIGWSD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QNE6M7I3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ee9f2c0ee00943f41dbc08dbe7b4f649e27f8011175edf9751abc57bffcd45e5","target":"graph","created_at":"2026-05-17T23:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive experiments show that this framework achieves superior solution quality compared with state-of-the-art learning-based methods, with a smaller gap to classical heuristics, demonstrating strong generalization across diverse CVRP variants."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Route-First Cluster-Second decomposition plus dynamic programming guidance will reliably mitigate partial observability and produce generalizable improvements without introducing new biases or overfitting to the tested CVRP variants."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A knowledge-embedded RL framework decomposes generalized CVRPs into route-first and cluster-second subproblems, using dynamic programming to guide the RL solver and a history-enhanced context module to handle partial observability, yielding better solutions than prior learning methods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A framework embedding classical routing knowledge into RL achieves better solutions for diverse CVRP variants."}],"snapshot_sha256":"a5a7cbe3e560807b7369002c3a1c2b30d7bb080094d48e4791871fcccf748068"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem with broad applications in logistics and transportation. Real-world CVRPs often involve diverse objectives and complex constraints, such as time windows or backhaul requirements, motivating the development of a unified solution framework. Recent reinforcement learning (RL) approaches have shown promise in combinatorial optimization, yet they rely on end-to-end learning and lack explicit problem-solving knowledge, limiting solution quality. In this paper, we propose a knowledge-embedded framework inspired by the Rou","authors_text":"Hao Hu, Liang Wang, Wen Wang, Xiangchen Wu, Xianping Tao","cross_cats":[],"headline":"A framework embedding classical routing knowledge into RL achieves better solutions for diverse CVRP variants.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:05:22Z","title":"A Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing Problems"},"references":{"count":42,"internal_anchors":0,"resolved_work":42,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Routefinder: Towards foundation models for vehicle routing problems","work_id":"65b94abc-7a2f-4393-bd62-6da2c721cfea","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Learn- ing to handle complex constraints for vehicle routing prob- lems.Advances in Neural Information Processing Sys- tems, 37:93479–93509,","work_id":"78783065-615f-42d4-8053-c9b54afe3327","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Learning to perform local rewriting for combinatorial opti- mization.Advances in neural information processing sys- tems, 32,","work_id":"6d943f93-f5a7-4c4c-bbd4-57d3c98f04b5","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Select and optimize: Learning to solve large-scale tsp instances","work_id":"87d25f8c-0301-493d-a781-843da427f284","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Learning 2-opt heuristics for the traveling salesman problem via deep re- inforcement learning","work_id":"f079835f-7cd1-4c98-8ea8-dc44846d6b10","year":2020}],"snapshot_sha256":"8db56c4f55f4230dde80621239975e5ce37b6a865226bbef87ac9b758da6e7ac"},"source":{"id":"2605.14416","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:06:16.113961Z","id":"def30479-0570-414b-a712-e49a8c6ca532","model_set":{"reader":"grok-4.3"},"one_line_summary":"A knowledge-embedded RL framework decomposes generalized CVRPs into route-first and cluster-second subproblems, using dynamic programming to guide the RL solver and a history-enhanced context module to handle partial observability, yielding better solutions than prior learning methods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A framework embedding classical routing knowledge into RL achieves better solutions for diverse CVRP variants.","strongest_claim":"Extensive experiments show that this framework achieves superior solution quality compared with state-of-the-art learning-based methods, with a smaller gap to classical heuristics, demonstrating strong generalization across diverse CVRP variants.","weakest_assumption":"That the Route-First Cluster-Second decomposition plus dynamic programming guidance will reliably mitigate partial observability and produce generalizable improvements without introducing new biases or overfitting to the tested CVRP variants."}},"verdict_id":"def30479-0570-414b-a712-e49a8c6ca532"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ed230d4cb14c80ca1459277812ec17e29bb129362355d5a8c0713c6e1a330dd1","target":"record","created_at":"2026-05-17T23:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f88afeb8bc5a0cdb2dba1101c43bc30c320a2c1924230ad1581bd593fb419220","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:05:22Z","title_canon_sha256":"6d597269492c269738a83d7a698cb3dc078be69e23ea18195e50a3a9e7de21a8"},"schema_version":"1.0","source":{"id":"2605.14416","kind":"arxiv","version":1}},"canonical_sha256":"8349e67d1be446835a430279106bc4a00e55747bd9d161c83f34c204a91946be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8349e67d1be446835a430279106bc4a00e55747bd9d161c83f34c204a91946be","first_computed_at":"2026-05-17T23:39:07.300744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.300744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yRahM4enr5OoJa6EznHW4zkF7D907Tjjt9SeWpIp0jCanOQqnQAQpYna7pgbixNIUIZi76CKuDGntdwFAXXXDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.301581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed230d4cb14c80ca1459277812ec17e29bb129362355d5a8c0713c6e1a330dd1","sha256:ee9f2c0ee00943f41dbc08dbe7b4f649e27f8011175edf9751abc57bffcd45e5"],"state_sha256":"7fa136ec37d7dd438a3547b23d6083922f3733d6f731c0310c507fd851bfa450"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"005D8Kmgg/H1oo8Vnr1tvnFqz8GBmXSUPf+Otgj0CICvlsXzx7fhi4Ac+Dd9I57jCZzN17DHnWTjVZ3+eSLICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T10:27:03.463269Z","bundle_sha256":"455a1da134300b980a3b24ac6acd4cacf22fddc13c6e0ba88a0044bc06a29a67"}}