{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZMJ4NYZRHWZX54IK74AJLNFQL6","short_pith_number":"pith:ZMJ4NYZR","schema_version":"1.0","canonical_sha256":"cb13c6e3313db37ef10aff0095b4b05f924c4bae34a827da71f099867f47c239","source":{"kind":"arxiv","id":"2508.08493","version":1},"attestation_state":"computed","paper":{"title":"POMO+: Leveraging starting nodes in POMO for solving Capacitated Vehicle Routing Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jan Wawszczak, Karol Ku\\'zniak, Pawe{\\l} Gora, Szymon Jakubicz","submitted_at":"2025-08-11T21:55:16Z","abstract_excerpt":"In recent years, reinforcement learning (RL) methods have emerged as a promising approach for solving combinatorial problems. Among RL-based models, POMO has demonstrated strong performance on a variety of tasks, including variants of the Vehicle Routing Problem (VRP). However, there is room for improvement for these tasks. In this work, we improved POMO, creating a method (\\textbf{POMO+}) that leverages the initial nodes to find a solution in a more informed way. We ran experiments on our new model and observed that our solution converges faster and achieves better results. We validated our m"},"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":"2508.08493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-11T21:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"44e40c0c8ce4c29e220365c5f303b1e02555972523f2b0921750ed3b1c6fe979","abstract_canon_sha256":"908f9fb8d29c779f7e953dfdbd13daf4d45ad7f704d3c97f68fafcb6c4301482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:29.487805Z","signature_b64":"5hx5dFsEjf6D5IDsW45h0mUZT2+hT95P/IjAXGcyzWixOnAudHOcjs7SqwVHXgiO9fVcbm/oANy3ivU+2VqQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb13c6e3313db37ef10aff0095b4b05f924c4bae34a827da71f099867f47c239","last_reissued_at":"2026-07-05T11:52:29.487248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:29.487248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POMO+: Leveraging starting nodes in POMO for solving Capacitated Vehicle Routing Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jan Wawszczak, Karol Ku\\'zniak, Pawe{\\l} Gora, Szymon Jakubicz","submitted_at":"2025-08-11T21:55:16Z","abstract_excerpt":"In recent years, reinforcement learning (RL) methods have emerged as a promising approach for solving combinatorial problems. Among RL-based models, POMO has demonstrated strong performance on a variety of tasks, including variants of the Vehicle Routing Problem (VRP). However, there is room for improvement for these tasks. In this work, we improved POMO, creating a method (\\textbf{POMO+}) that leverages the initial nodes to find a solution in a more informed way. We ran experiments on our new model and observed that our solution converges faster and achieves better results. We validated our m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08493","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/2508.08493/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":"2508.08493","created_at":"2026-07-05T11:52:29.487307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08493v1","created_at":"2026-07-05T11:52:29.487307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08493","created_at":"2026-07-05T11:52:29.487307+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMJ4NYZRHWZX","created_at":"2026-07-05T11:52:29.487307+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMJ4NYZRHWZX54IK","created_at":"2026-07-05T11:52:29.487307+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMJ4NYZR","created_at":"2026-07-05T11:52:29.487307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08492","citing_title":"Momentum Point-Perplexity Mechanics in Large Language Models","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6","json":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6.json","graph_json":"https://pith.science/api/pith-number/ZMJ4NYZRHWZX54IK74AJLNFQL6/graph.json","events_json":"https://pith.science/api/pith-number/ZMJ4NYZRHWZX54IK74AJLNFQL6/events.json","paper":"https://pith.science/paper/ZMJ4NYZR"},"agent_actions":{"view_html":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6","download_json":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6.json","view_paper":"https://pith.science/paper/ZMJ4NYZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08493&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMJ4NYZRHWZX54IK74AJLNFQL6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMJ4NYZRHWZX54IK74AJLNFQL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6/action/storage_attestation","attest_author":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6/action/author_attestation","sign_citation":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6/action/citation_signature","submit_replication":"https://pith.science/pith/ZMJ4NYZRHWZX54IK74AJLNFQL6/action/replication_record"}},"created_at":"2026-07-05T11:52:29.487307+00:00","updated_at":"2026-07-05T11:52:29.487307+00:00"}