{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZYGI7GDFMT4DDDNSWFLS4HA7KA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4a8862208b98700eff74a494b7870c33cba3f365a2240feb08c0768908b52cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-21T16:34:00Z","title_canon_sha256":"9ec53ac2747a1633d8e4e00ab6787dbee4d4c7e1b7ee82fc2505191314f977e7"},"schema_version":"1.0","source":{"id":"2511.17367","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.17367","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2511.17367v2","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.17367","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZYGI7GDFMT4D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZYGI7GDFMT4DDDNS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZYGI7GDF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b3b43c61816c8d2e2fc3906b7f3942944bf4329a7aa5579708031a2098935ff3","target":"graph","created_at":"2026-05-17T23:39:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"After reinforcement learning, our policy achieves robust zero-shot generalization to unseen real-world graph structures and consistently outperforms the policy directly trained on the test graphs by the existing game RL approach."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The belief preservation mechanism successfully extends the optimality properties of the dynamic programming strategies to the partially observable setting while preserving worst-case robustness against asynchronous evader moves."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"R2PS combines a proof that dynamic programming remains optimal under asynchronous evader moves, a belief preservation mechanism for partial observability, and integration into equilibrium policy generalization to produce real-time pursuer policies that zero-shot generalize to unseen graphs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Belief preservation extends dynamic programming to partial observability for real-time robust pursuit policies."}],"snapshot_sha256":"f14c27d8e7c62e7a97bae9327972bfc618e7ec7a4acf162cda7f10526adf01c9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Computing worst-case robust strategies in pursuit-evasion games (PEGs) is time-consuming, especially when real-world factors like partial observability are considered. While important for general security purposes, real-time applicable pursuit strategies for graph-based PEGs are currently missing when the pursuers only have imperfect information about the evader's position. Although state-of-the-art reinforcement learning (RL) methods like Equilibrium Policy Generalization (EPG) and Grasper provide guidelines for learning graph neural network (GNN) policies robust to different game dynamics, t","authors_text":"Dongbin Zhao, Runyu Lu, Ruochuan Shi, Yuanheng Zhu","cross_cats":[],"headline":"Belief preservation extends dynamic programming to partial observability for real-time robust pursuit policies.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-21T16:34:00Z","title":"R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability"},"references":{"count":8,"internal_anchors":1,"resolved_work":8,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Self-learning exploration and mapping for mobile robots via deep reinforcement learning","work_id":"ba50ce7d-0ee4-43ef-886d-f109c64c5d40","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Soft actor-critic for discrete action settings.arXiv preprint arXiv:1910.07207,","work_id":"684554b0-ea6b-4199-b360-8e61b4bd9971","year":1910},{"cited_arxiv_id":"1812.05905","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Soft Actor-Critic Algorithms and Applications","work_id":"bb49c9fb-03b2-4226-9edb-50186b8193e4","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Pursuit-evasion games with unmanned ground and aerial vehicles","work_id":"1d61f8c8-6e59-47ed-a30b-b2c5bebd63a2","year":2001},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Solving urban network security games: Learning platform, benchmark, and challenge for AI research.arXiv preprint arXiv:2501.17559,","work_id":"bc133bbb-6108-4a06-bb6c-ac3662967a2b","year":null}],"snapshot_sha256":"536094c12974b0cdb502a0af7eca5a8d25c404c9f71470c1ac7b89526790e82f"},"source":{"id":"2511.17367","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T20:15:50.816748Z","id":"842f93f8-75ea-40ad-929b-16bf2f5f81b4","model_set":{"reader":"grok-4.3"},"one_line_summary":"R2PS combines a proof that dynamic programming remains optimal under asynchronous evader moves, a belief preservation mechanism for partial observability, and integration into equilibrium policy generalization to produce real-time pursuer policies that zero-shot generalize to unseen graphs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Belief preservation extends dynamic programming to partial observability for real-time robust pursuit policies.","strongest_claim":"After reinforcement learning, our policy achieves robust zero-shot generalization to unseen real-world graph structures and consistently outperforms the policy directly trained on the test graphs by the existing game RL approach.","weakest_assumption":"The belief preservation mechanism successfully extends the optimality properties of the dynamic programming strategies to the partially observable setting while preserving worst-case robustness against asynchronous evader moves."}},"verdict_id":"842f93f8-75ea-40ad-929b-16bf2f5f81b4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5571c2ddb47cc3624b14b0f6560ed919985307dde80adeff518c82d47e9e2952","target":"record","created_at":"2026-05-17T23:39:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4a8862208b98700eff74a494b7870c33cba3f365a2240feb08c0768908b52cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-21T16:34:00Z","title_canon_sha256":"9ec53ac2747a1633d8e4e00ab6787dbee4d4c7e1b7ee82fc2505191314f977e7"},"schema_version":"1.0","source":{"id":"2511.17367","kind":"arxiv","version":2}},"canonical_sha256":"ce0c8f986564f8318db2b1572e1c1f5002fd766b0e0b1de7890a31a3c898dcce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce0c8f986564f8318db2b1572e1c1f5002fd766b0e0b1de7890a31a3c898dcce","first_computed_at":"2026-05-17T23:39:00.721826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:00.721826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8YE42UDRZ8urkBZa2EJinJmTUyU5MAuPS3v4Bcz32b8rmIKTY7X3/EtWgG7bG4aMpbTgRy4lLvAHjggUx9cUDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:00.722726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.17367","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5571c2ddb47cc3624b14b0f6560ed919985307dde80adeff518c82d47e9e2952","sha256:b3b43c61816c8d2e2fc3906b7f3942944bf4329a7aa5579708031a2098935ff3"],"state_sha256":"c545732b05239138cd341becc83dc5cda4bd68af059f36678553be763674125d"}