{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C4IOAXPTA3QHI2NWAD67GJVP3V","short_pith_number":"pith:C4IOAXPT","schema_version":"1.0","canonical_sha256":"1710e05df306e07469b600fdf326afdd64b64a7e6e323328b62cf114acf9b4e1","source":{"kind":"arxiv","id":"2506.08424","version":2},"attestation_state":"computed","paper":{"title":"SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianan Zhou, Mohammed Haroon Dupty, Wee Sun Lee, Yining Ma, Yong Liang Goh, Zhiguang Cao","submitted_at":"2025-06-10T03:55:14Z","abstract_excerpt":"Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-world customer distributions. In this work, we advance the Multi-Task VRP (MTVRP) setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP (MTMDVRP) setting, and introduce SHIELD, a novel model that leverages both sparsity and hierarchy principles. Building on a deeper decoder architecture, we first incorporate the Mixture-of-Depths (MoD) technique to enforce sparsity. This improves both efficie"},"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":"2506.08424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-10T03:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"b67817b73a7f6103b7e25e909b0bfd75229c51f451e9504f3e06479d1bc9b584","abstract_canon_sha256":"1e6ab8abea2b6db6066c0bb6714c94d3e284f28dbc2080a6fb7e3a112b7d00cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:29.572233Z","signature_b64":"EU6PGmsHQIaVyN/97wlpgrsHv5xSCgf6qbGR1fnu18cpsjH0mhpVNofhzw/CUdtW94HN/EnimJ3sCa4DYzxtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1710e05df306e07469b600fdf326afdd64b64a7e6e323328b62cf114acf9b4e1","last_reissued_at":"2026-07-05T11:19:29.571640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:29.571640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianan Zhou, Mohammed Haroon Dupty, Wee Sun Lee, Yining Ma, Yong Liang Goh, Zhiguang Cao","submitted_at":"2025-06-10T03:55:14Z","abstract_excerpt":"Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-world customer distributions. In this work, we advance the Multi-Task VRP (MTVRP) setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP (MTMDVRP) setting, and introduce SHIELD, a novel model that leverages both sparsity and hierarchy principles. Building on a deeper decoder architecture, we first incorporate the Mixture-of-Depths (MoD) technique to enforce sparsity. This improves both efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08424","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/2506.08424/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":"2506.08424","created_at":"2026-07-05T11:19:29.571707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08424v2","created_at":"2026-07-05T11:19:29.571707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08424","created_at":"2026-07-05T11:19:29.571707+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4IOAXPTA3QH","created_at":"2026-07-05T11:19:29.571707+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4IOAXPTA3QHI2NW","created_at":"2026-07-05T11:19:29.571707+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4IOAXPT","created_at":"2026-07-05T11:19:29.571707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01162","citing_title":"Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V","json":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V.json","graph_json":"https://pith.science/api/pith-number/C4IOAXPTA3QHI2NWAD67GJVP3V/graph.json","events_json":"https://pith.science/api/pith-number/C4IOAXPTA3QHI2NWAD67GJVP3V/events.json","paper":"https://pith.science/paper/C4IOAXPT"},"agent_actions":{"view_html":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V","download_json":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V.json","view_paper":"https://pith.science/paper/C4IOAXPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08424&json=true","fetch_graph":"https://pith.science/api/pith-number/C4IOAXPTA3QHI2NWAD67GJVP3V/graph.json","fetch_events":"https://pith.science/api/pith-number/C4IOAXPTA3QHI2NWAD67GJVP3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V/action/storage_attestation","attest_author":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V/action/author_attestation","sign_citation":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V/action/citation_signature","submit_replication":"https://pith.science/pith/C4IOAXPTA3QHI2NWAD67GJVP3V/action/replication_record"}},"created_at":"2026-07-05T11:19:29.571707+00:00","updated_at":"2026-07-05T11:19:29.571707+00:00"}