{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K53C44D6IHMZELHDQM5ENRZKHV","short_pith_number":"pith:K53C44D6","schema_version":"1.0","canonical_sha256":"57762e707e41d9922ce3833a46c72a3d59dd4e6c4b4bee33a369d850094dc6a4","source":{"kind":"arxiv","id":"2402.09765","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Solving Stochastic Vehicle Routing Problem with Time Windows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ikboljon Sobirov, Martin Takac, Ruben Solozabal, Zangir Iklassov","submitted_at":"2024-02-15T07:35:29Z","abstract_excerpt":"This paper introduces a reinforcement learning approach to optimize the Stochastic Vehicle Routing Problem with Time Windows (SVRP), focusing on reducing travel costs in goods delivery. We develop a novel SVRP formulation that accounts for uncertain travel costs and demands, alongside specific customer time windows. An attention-based neural network trained through reinforcement learning is employed to minimize routing costs. Our approach addresses a gap in SVRP research, which traditionally relies on heuristic methods, by leveraging machine learning. The model outperforms the Ant-Colony Optim"},"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":"2402.09765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-15T07:35:29Z","cross_cats_sorted":[],"title_canon_sha256":"1306f487779534f1269e42b7b6d1d40bb7f506bf3c8de706203971177371fbf1","abstract_canon_sha256":"7a339da5110cbca20cf9532c4ed661653690697c8140250f8775428b4873a096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:36.595026Z","signature_b64":"O7wMDDkqCmQuQeoRgLUUxQviR4rH8oa+1m64+eJukVGr2RF83Ewv4ENUMflDVHpJngxertVlum5m0CMPEzCAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57762e707e41d9922ce3833a46c72a3d59dd4e6c4b4bee33a369d850094dc6a4","last_reissued_at":"2026-07-05T07:45:36.594600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:36.594600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Solving Stochastic Vehicle Routing Problem with Time Windows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ikboljon Sobirov, Martin Takac, Ruben Solozabal, Zangir Iklassov","submitted_at":"2024-02-15T07:35:29Z","abstract_excerpt":"This paper introduces a reinforcement learning approach to optimize the Stochastic Vehicle Routing Problem with Time Windows (SVRP), focusing on reducing travel costs in goods delivery. We develop a novel SVRP formulation that accounts for uncertain travel costs and demands, alongside specific customer time windows. An attention-based neural network trained through reinforcement learning is employed to minimize routing costs. Our approach addresses a gap in SVRP research, which traditionally relies on heuristic methods, by leveraging machine learning. The model outperforms the Ant-Colony Optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09765","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/2402.09765/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":"2402.09765","created_at":"2026-07-05T07:45:36.594657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09765v1","created_at":"2026-07-05T07:45:36.594657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09765","created_at":"2026-07-05T07:45:36.594657+00:00"},{"alias_kind":"pith_short_12","alias_value":"K53C44D6IHMZ","created_at":"2026-07-05T07:45:36.594657+00:00"},{"alias_kind":"pith_short_16","alias_value":"K53C44D6IHMZELHD","created_at":"2026-07-05T07:45:36.594657+00:00"},{"alias_kind":"pith_short_8","alias_value":"K53C44D6","created_at":"2026-07-05T07:45:36.594657+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/K53C44D6IHMZELHDQM5ENRZKHV","json":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV.json","graph_json":"https://pith.science/api/pith-number/K53C44D6IHMZELHDQM5ENRZKHV/graph.json","events_json":"https://pith.science/api/pith-number/K53C44D6IHMZELHDQM5ENRZKHV/events.json","paper":"https://pith.science/paper/K53C44D6"},"agent_actions":{"view_html":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV","download_json":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV.json","view_paper":"https://pith.science/paper/K53C44D6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09765&json=true","fetch_graph":"https://pith.science/api/pith-number/K53C44D6IHMZELHDQM5ENRZKHV/graph.json","fetch_events":"https://pith.science/api/pith-number/K53C44D6IHMZELHDQM5ENRZKHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV/action/storage_attestation","attest_author":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV/action/author_attestation","sign_citation":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV/action/citation_signature","submit_replication":"https://pith.science/pith/K53C44D6IHMZELHDQM5ENRZKHV/action/replication_record"}},"created_at":"2026-07-05T07:45:36.594657+00:00","updated_at":"2026-07-05T07:45:36.594657+00:00"}