{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OQF3VTS6XUH5YGJ2GSEGI7MBSW","short_pith_number":"pith:OQF3VTS6","schema_version":"1.0","canonical_sha256":"740bbace5ebd0fdc193a3488647d81959c4f861ec7423ed6ddd438982ccd7054","source":{"kind":"arxiv","id":"2102.11756","version":2},"attestation_state":"computed","paper":{"title":"Deep Policy Dynamic Programming for Vehicle Routing Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Herke van Hoof, Joaquim Gromicho, Max Welling, Wouter Kool","submitted_at":"2021-02-23T15:33:57Z","abstract_excerpt":"Routing problems are a class of combinatorial problems with many practical applications. Recently, end-to-end deep learning methods have been proposed to learn approximate solution heuristics for such problems. In contrast, classical dynamic programming (DP) algorithms guarantee optimal solutions, but scale badly with the problem size. We propose Deep Policy Dynamic Programming (DPDP), which aims to combine the strengths of learned neural heuristics with those of DP algorithms. DPDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained"},"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":"2102.11756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-23T15:33:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d898b0c0905b1b3278e1e868fe7fbde755cbfba7c58ac77d531c14a7fd0c7e64","abstract_canon_sha256":"3613f5d9bce941224200f42e94d7c5ee2ae0405fbc239262b4bce06b04a3ecb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:11.056874Z","signature_b64":"/iD4C7o2AKxFjHWw496Pg+PIQMa4PjIksC48olvqDdke5GxCgvV8zBld9EoxW/++NjJRX4w971ZZI9NstoOyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740bbace5ebd0fdc193a3488647d81959c4f861ec7423ed6ddd438982ccd7054","last_reissued_at":"2026-07-05T03:37:11.056348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:11.056348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Policy Dynamic Programming for Vehicle Routing Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Herke van Hoof, Joaquim Gromicho, Max Welling, Wouter Kool","submitted_at":"2021-02-23T15:33:57Z","abstract_excerpt":"Routing problems are a class of combinatorial problems with many practical applications. Recently, end-to-end deep learning methods have been proposed to learn approximate solution heuristics for such problems. In contrast, classical dynamic programming (DP) algorithms guarantee optimal solutions, but scale badly with the problem size. We propose Deep Policy Dynamic Programming (DPDP), which aims to combine the strengths of learned neural heuristics with those of DP algorithms. DPDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11756","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/2102.11756/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":"2102.11756","created_at":"2026-07-05T03:37:11.056421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11756v2","created_at":"2026-07-05T03:37:11.056421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11756","created_at":"2026-07-05T03:37:11.056421+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQF3VTS6XUH5","created_at":"2026-07-05T03:37:11.056421+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQF3VTS6XUH5YGJ2","created_at":"2026-07-05T03:37:11.056421+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQF3VTS6","created_at":"2026-07-05T03:37:11.056421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10520","citing_title":"Nonlocal Monte Carlo via Reinforcement Learning","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW","json":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW.json","graph_json":"https://pith.science/api/pith-number/OQF3VTS6XUH5YGJ2GSEGI7MBSW/graph.json","events_json":"https://pith.science/api/pith-number/OQF3VTS6XUH5YGJ2GSEGI7MBSW/events.json","paper":"https://pith.science/paper/OQF3VTS6"},"agent_actions":{"view_html":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW","download_json":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW.json","view_paper":"https://pith.science/paper/OQF3VTS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11756&json=true","fetch_graph":"https://pith.science/api/pith-number/OQF3VTS6XUH5YGJ2GSEGI7MBSW/graph.json","fetch_events":"https://pith.science/api/pith-number/OQF3VTS6XUH5YGJ2GSEGI7MBSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW/action/storage_attestation","attest_author":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW/action/author_attestation","sign_citation":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW/action/citation_signature","submit_replication":"https://pith.science/pith/OQF3VTS6XUH5YGJ2GSEGI7MBSW/action/replication_record"}},"created_at":"2026-07-05T03:37:11.056421+00:00","updated_at":"2026-07-05T03:37:11.056421+00:00"}