{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NTXAYLJKZO4AHNPU4C2I5GB56K","short_pith_number":"pith:NTXAYLJK","schema_version":"1.0","canonical_sha256":"6cee0c2d2acbb803b5f4e0b48e983df28799d54fdc305f688abf0039a99d8208","source":{"kind":"arxiv","id":"2605.26776","version":1},"attestation_state":"computed","paper":{"title":"Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhao Miao, Chen Chen, Fang Deng, Tongyu Wu, Yuntian Zhang","submitted_at":"2026-05-26T09:46:54Z","abstract_excerpt":"In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cro"},"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":"2605.26776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:46:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07e315843f102295ff8dd451f3be3465d91a406ea180627ae2e1c20af0a3f353","abstract_canon_sha256":"c875ed92eec73187d18d142fd0e39f30a727648acb60c47aa30b0a468d0d73b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:12.077402Z","signature_b64":"SvttStzbYcLrliO4TG+e8bUI8cr7zlbgADlbVH9NVj3bDtdUyxglYaxkEhI4BXkaLsXDEDAIaXFhKSljmEBRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cee0c2d2acbb803b5f4e0b48e983df28799d54fdc305f688abf0039a99d8208","last_reissued_at":"2026-05-27T01:06:12.076649Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:12.076649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhao Miao, Chen Chen, Fang Deng, Tongyu Wu, Yuntian Zhang","submitted_at":"2026-05-26T09:46:54Z","abstract_excerpt":"In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26776","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/2605.26776/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":"2605.26776","created_at":"2026-05-27T01:06:12.076783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26776v1","created_at":"2026-05-27T01:06:12.076783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26776","created_at":"2026-05-27T01:06:12.076783+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTXAYLJKZO4A","created_at":"2026-05-27T01:06:12.076783+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTXAYLJKZO4AHNPU","created_at":"2026-05-27T01:06:12.076783+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTXAYLJK","created_at":"2026-05-27T01:06:12.076783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K","json":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K.json","graph_json":"https://pith.science/api/pith-number/NTXAYLJKZO4AHNPU4C2I5GB56K/graph.json","events_json":"https://pith.science/api/pith-number/NTXAYLJKZO4AHNPU4C2I5GB56K/events.json","paper":"https://pith.science/paper/NTXAYLJK"},"agent_actions":{"view_html":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K","download_json":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K.json","view_paper":"https://pith.science/paper/NTXAYLJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26776&json=true","fetch_graph":"https://pith.science/api/pith-number/NTXAYLJKZO4AHNPU4C2I5GB56K/graph.json","fetch_events":"https://pith.science/api/pith-number/NTXAYLJKZO4AHNPU4C2I5GB56K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K/action/storage_attestation","attest_author":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K/action/author_attestation","sign_citation":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K/action/citation_signature","submit_replication":"https://pith.science/pith/NTXAYLJKZO4AHNPU4C2I5GB56K/action/replication_record"}},"created_at":"2026-05-27T01:06:12.076783+00:00","updated_at":"2026-05-27T01:06:12.076783+00:00"}