{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BYNKXNHNW3NR5VYBZITBF3IL2E","short_pith_number":"pith:BYNKXNHN","schema_version":"1.0","canonical_sha256":"0e1aabb4edb6db1ed701ca2612ed0bd11978243c80469a7be77c894edeb4a81e","source":{"kind":"arxiv","id":"2405.13947","version":2},"attestation_state":"computed","paper":{"title":"Leader Reward for POMO-Based Neural Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaoyang Wang, Jingze Li, Pengzhi Cheng, Weiwei Sun","submitted_at":"2024-05-22T19:27:03Z","abstract_excerpt":"Deep neural networks based on reinforcement learning (RL) for solving combinatorial optimization (CO) problems are developing rapidly and have shown a tendency to approach or even outperform traditional solvers. However, existing methods overlook an important distinction: CO problems differ from other traditional problems in that they focus solely on the optimal solution provided by the model within a specific length of time, rather than considering the overall quality of all solutions generated by the model. In this paper, we propose Leader Reward and apply it during two different training ph"},"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":"2405.13947","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"e3af4e548bc501a0c060326a9df290451b1e233e08aab1362551e1486dfcfba7","abstract_canon_sha256":"e4000a077c3437f43e713dce587971242eb9e7ee0deddc8fde5ec93ba521d8d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:48.222424Z","signature_b64":"wXiKB7fz58I0F+fxnADbUu7kXowu1zFuIE1vQm2+QOm/QCvsuELdiaBCUqFhHGzkty/MvtGLAC33XurxG+A+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1aabb4edb6db1ed701ca2612ed0bd11978243c80469a7be77c894edeb4a81e","last_reissued_at":"2026-06-30T02:16:48.221571Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:48.221571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leader Reward for POMO-Based Neural Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaoyang Wang, Jingze Li, Pengzhi Cheng, Weiwei Sun","submitted_at":"2024-05-22T19:27:03Z","abstract_excerpt":"Deep neural networks based on reinforcement learning (RL) for solving combinatorial optimization (CO) problems are developing rapidly and have shown a tendency to approach or even outperform traditional solvers. However, existing methods overlook an important distinction: CO problems differ from other traditional problems in that they focus solely on the optimal solution provided by the model within a specific length of time, rather than considering the overall quality of all solutions generated by the model. In this paper, we propose Leader Reward and apply it during two different training ph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13947","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/2405.13947/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":"2405.13947","created_at":"2026-06-30T02:16:48.221699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13947v2","created_at":"2026-06-30T02:16:48.221699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13947","created_at":"2026-06-30T02:16:48.221699+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYNKXNHNW3NR","created_at":"2026-06-30T02:16:48.221699+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYNKXNHNW3NR5VYB","created_at":"2026-06-30T02:16:48.221699+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYNKXNHN","created_at":"2026-06-30T02:16:48.221699+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/BYNKXNHNW3NR5VYBZITBF3IL2E","json":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E.json","graph_json":"https://pith.science/api/pith-number/BYNKXNHNW3NR5VYBZITBF3IL2E/graph.json","events_json":"https://pith.science/api/pith-number/BYNKXNHNW3NR5VYBZITBF3IL2E/events.json","paper":"https://pith.science/paper/BYNKXNHN"},"agent_actions":{"view_html":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E","download_json":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E.json","view_paper":"https://pith.science/paper/BYNKXNHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13947&json=true","fetch_graph":"https://pith.science/api/pith-number/BYNKXNHNW3NR5VYBZITBF3IL2E/graph.json","fetch_events":"https://pith.science/api/pith-number/BYNKXNHNW3NR5VYBZITBF3IL2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E/action/storage_attestation","attest_author":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E/action/author_attestation","sign_citation":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E/action/citation_signature","submit_replication":"https://pith.science/pith/BYNKXNHNW3NR5VYBZITBF3IL2E/action/replication_record"}},"created_at":"2026-06-30T02:16:48.221699+00:00","updated_at":"2026-06-30T02:16:48.221699+00:00"}