{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GHUK42ARTMTROFTSY2H6PT4WZN","short_pith_number":"pith:GHUK42AR","canonical_record":{"source":{"id":"2505.06319","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T21:12:34Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"012489dc205a0d8dda91db492a986b72afc7170b03be639520d8704251974e3c","abstract_canon_sha256":"8c3610cdd1bab1ada5a2633bb4064e57cba67826a62e78b3049f2c4db6b81906"},"schema_version":"1.0"},"canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","source":{"kind":"arxiv","id":"2505.06319","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06319","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06319v1","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06319","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"GHUK42ARTMTR","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"GHUK42ARTMTROFTS","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"GHUK42AR","created_at":"2026-07-05T11:01:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GHUK42ARTMTROFTSY2H6PT4WZN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06319","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T21:12:34Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"012489dc205a0d8dda91db492a986b72afc7170b03be639520d8704251974e3c","abstract_canon_sha256":"8c3610cdd1bab1ada5a2633bb4064e57cba67826a62e78b3049f2c4db6b81906"},"schema_version":"1.0"},"canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:07.351249Z","signature_b64":"4P2Oa90TYJDQgUAEvgHkWk1afH58gTDa0S/GFw9yo0I/QVbqx+h1XaYy9Vrrxs/jgu3bx40TlZ2Z9C8+LZkiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","last_reissued_at":"2026-07-05T11:01:07.350822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:07.350822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06319","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/p7ZdlWHwgQtcg3uZ47XX5Ed3fd82mAFkbHUcKSTYXDKxiEuc7e1pXkeNpkhXhQcSo9LYTnoFNs4zuI3vwlcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:02:13.445990Z"},"content_sha256":"518ec32e112771e8f3b36b847752483a9150260d998b874c6dc09db8f1b2ece2","schema_version":"1.0","event_id":"sha256:518ec32e112771e8f3b36b847752483a9150260d998b874c6dc09db8f1b2ece2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GHUK42ARTMTROFTSY2H6PT4WZN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Lifeng Zhou, Zijian An","submitted_at":"2025-05-08T21:12:34Z","abstract_excerpt":"Game-theoretic resource allocation on graphs (GRAG) involves two players competing over multiple steps to control nodes of interest on a graph, a problem modeled as a multi-step Colonel Blotto Game (MCBG). Finding optimal strategies is challenging due to the dynamic action space and structural constraints imposed by the graph. To address this, we formulate the MCBG as a Markov Decision Process (MDP) and apply Reinforcement Learning (RL) methods, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). To enforce graph constraints, we introduce an action-displacement adjacency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06319","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/2505.06319/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JtdyUfBmhi8AJRW8cWBOqMi8LVKfuKo8BMO+L33IM9+8G86UeRG9YcQ1cm5yRHkAiQRZqKU7AgW+lxFczlUkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:02:13.446502Z"},"content_sha256":"c98f7fc23127c46185511f0d46c67e92ba352439a296acf3d41c2a830506611b","schema_version":"1.0","event_id":"sha256:c98f7fc23127c46185511f0d46c67e92ba352439a296acf3d41c2a830506611b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/bundle.json","state_url":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHUK42ARTMTROFTSY2H6PT4WZN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T03:02:13Z","links":{"resolver":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN","bundle":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/bundle.json","state":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHUK42ARTMTROFTSY2H6PT4WZN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GHUK42ARTMTROFTSY2H6PT4WZN","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":"8c3610cdd1bab1ada5a2633bb4064e57cba67826a62e78b3049f2c4db6b81906","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T21:12:34Z","title_canon_sha256":"012489dc205a0d8dda91db492a986b72afc7170b03be639520d8704251974e3c"},"schema_version":"1.0","source":{"id":"2505.06319","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06319","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06319v1","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06319","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"GHUK42ARTMTR","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"GHUK42ARTMTROFTS","created_at":"2026-07-05T11:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"GHUK42AR","created_at":"2026-07-05T11:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:c98f7fc23127c46185511f0d46c67e92ba352439a296acf3d41c2a830506611b","target":"graph","created_at":"2026-07-05T11:01:07Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.06319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Game-theoretic resource allocation on graphs (GRAG) involves two players competing over multiple steps to control nodes of interest on a graph, a problem modeled as a multi-step Colonel Blotto Game (MCBG). Finding optimal strategies is challenging due to the dynamic action space and structural constraints imposed by the graph. To address this, we formulate the MCBG as a Markov Decision Process (MDP) and apply Reinforcement Learning (RL) methods, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). To enforce graph constraints, we introduce an action-displacement adjacency ","authors_text":"Lifeng Zhou, Zijian An","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T21:12:34Z","title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06319","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:518ec32e112771e8f3b36b847752483a9150260d998b874c6dc09db8f1b2ece2","target":"record","created_at":"2026-07-05T11:01:07Z","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":"8c3610cdd1bab1ada5a2633bb4064e57cba67826a62e78b3049f2c4db6b81906","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T21:12:34Z","title_canon_sha256":"012489dc205a0d8dda91db492a986b72afc7170b03be639520d8704251974e3c"},"schema_version":"1.0","source":{"id":"2505.06319","kind":"arxiv","version":1}},"canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","first_computed_at":"2026-07-05T11:01:07.350822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:07.350822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4P2Oa90TYJDQgUAEvgHkWk1afH58gTDa0S/GFw9yo0I/QVbqx+h1XaYy9Vrrxs/jgu3bx40TlZ2Z9C8+LZkiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:07.351249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06319","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:518ec32e112771e8f3b36b847752483a9150260d998b874c6dc09db8f1b2ece2","sha256:c98f7fc23127c46185511f0d46c67e92ba352439a296acf3d41c2a830506611b"],"state_sha256":"8a7fd9caec03a6a95102c2542805daa16a85b29d3268e3f8201976b60f7300f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1z+Nb4H0e/T9mf14xbYnAlOzPEwlBg2E0kwCusF3vaazMSuEFoXqgfhyp50rHeQeGBtQ0/yoHaL4jQAxKLcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:02:13.451490Z","bundle_sha256":"f43e57684996fb47c8c911dda6357111a1c01f65d0d6e33c257853594b6d85cf"}}