{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NIFYGAROIEEFW7KLYDAYGKIBY4","short_pith_number":"pith:NIFYGARO","canonical_record":{"source":{"id":"2506.00797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:58:20Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"ed7b9c75f73465d6a6807649d4d2c42b6b9ef4c041a2379d9ca59a575a13129e","abstract_canon_sha256":"36e4155d51c6cccc2b4a1d057d22b61e5aaa0da5deca344abfda240487dbf30c"},"schema_version":"1.0"},"canonical_sha256":"6a0b83022e41085b7d4bc0c1832901c7079f2726a0e699f9d32fe1f0ed436fa0","source":{"kind":"arxiv","id":"2506.00797","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00797","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00797v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00797","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"NIFYGAROIEEF","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"NIFYGAROIEEFW7KL","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"NIFYGARO","created_at":"2026-07-05T11:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NIFYGAROIEEFW7KLYDAYGKIBY4","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:58:20Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"ed7b9c75f73465d6a6807649d4d2c42b6b9ef4c041a2379d9ca59a575a13129e","abstract_canon_sha256":"36e4155d51c6cccc2b4a1d057d22b61e5aaa0da5deca344abfda240487dbf30c"},"schema_version":"1.0"},"canonical_sha256":"6a0b83022e41085b7d4bc0c1832901c7079f2726a0e699f9d32fe1f0ed436fa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:40.603075Z","signature_b64":"5cSrD2EDL0uYpDmnq68AUdVAOR4dkZntstRXqoNa1oGr+4xbo9DK+iw+TPpzymAIZ99jnPHqmtsN5N4YmvOGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a0b83022e41085b7d4bc0c1832901c7079f2726a0e699f9d32fe1f0ed436fa0","last_reissued_at":"2026-07-05T11:13:40.602516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:40.602516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00797","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":"2026-07-05T11:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p+hq8HWC8A+FzxIRZzTLwBWiCeysIe5LlIULO7c1qzNtSJ/SVFBJEET6LNLI8lMv8Se7fDmwb+Ai8FNqlbwGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:42:01.788637Z"},"content_sha256":"7dfd9f40e47c82adbed39c5f608dc93b6a139c73e6f4766bfb323948608b32ca","schema_version":"1.0","event_id":"sha256:7dfd9f40e47c82adbed39c5f608dc93b6a139c73e6f4766bfb323948608b32ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NIFYGAROIEEFW7KLYDAYGKIBY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Gangshan Jing, Jianglin Ding, Jingcheng Tang","submitted_at":"2025-06-01T02:58:20Z","abstract_excerpt":"Action-dependent individual policies, which incorporate both environmental states and the actions of other agents in decision-making, have emerged as a promising paradigm for achieving global optimality in multi-agent reinforcement learning (MARL). However, the existing literature often adopts auto-regressive action-dependent policies, where each agent's policy depends on the actions of all preceding agents. This formulation incurs substantial computational complexity as the number of agents increases, thereby limiting scalability. In this work, we consider a more generalized class of action-d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00797","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/2506.00797/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":"2026-07-05T11:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnb8lNyJWR+95pT9b7JP0dzNZ6pPDEEng5Uf9KEd1AA4zWmMOnIF2ndYgkvLvacQHMrQIudyhBFIRQJjUPdaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:42:01.789223Z"},"content_sha256":"971ce2dbcfe8060ac2911f52d03a7e706985c5081c71c8083c3141f3acfb969a","schema_version":"1.0","event_id":"sha256:971ce2dbcfe8060ac2911f52d03a7e706985c5081c71c8083c3141f3acfb969a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIFYGAROIEEFW7KLYDAYGKIBY4/bundle.json","state_url":"https://pith.science/pith/NIFYGAROIEEFW7KLYDAYGKIBY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIFYGAROIEEFW7KLYDAYGKIBY4/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":"2026-08-08T09:42:01Z","links":{"resolver":"https://pith.science/pith/NIFYGAROIEEFW7KLYDAYGKIBY4","bundle":"https://pith.science/pith/NIFYGAROIEEFW7KLYDAYGKIBY4/bundle.json","state":"https://pith.science/pith/NIFYGAROIEEFW7KLYDAYGKIBY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIFYGAROIEEFW7KLYDAYGKIBY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NIFYGAROIEEFW7KLYDAYGKIBY4","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":"36e4155d51c6cccc2b4a1d057d22b61e5aaa0da5deca344abfda240487dbf30c","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:58:20Z","title_canon_sha256":"ed7b9c75f73465d6a6807649d4d2c42b6b9ef4c041a2379d9ca59a575a13129e"},"schema_version":"1.0","source":{"id":"2506.00797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00797","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00797v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00797","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"NIFYGAROIEEF","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"NIFYGAROIEEFW7KL","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"NIFYGARO","created_at":"2026-07-05T11:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:971ce2dbcfe8060ac2911f52d03a7e706985c5081c71c8083c3141f3acfb969a","target":"graph","created_at":"2026-07-05T11:13:40Z","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/2506.00797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Action-dependent individual policies, which incorporate both environmental states and the actions of other agents in decision-making, have emerged as a promising paradigm for achieving global optimality in multi-agent reinforcement learning (MARL). However, the existing literature often adopts auto-regressive action-dependent policies, where each agent's policy depends on the actions of all preceding agents. This formulation incurs substantial computational complexity as the number of agents increases, thereby limiting scalability. In this work, we consider a more generalized class of action-d","authors_text":"Gangshan Jing, Jianglin Ding, Jingcheng Tang","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:58:20Z","title":"Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00797","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":"sha256:7dfd9f40e47c82adbed39c5f608dc93b6a139c73e6f4766bfb323948608b32ca","target":"record","created_at":"2026-07-05T11:13:40Z","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":"36e4155d51c6cccc2b4a1d057d22b61e5aaa0da5deca344abfda240487dbf30c","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T02:58:20Z","title_canon_sha256":"ed7b9c75f73465d6a6807649d4d2c42b6b9ef4c041a2379d9ca59a575a13129e"},"schema_version":"1.0","source":{"id":"2506.00797","kind":"arxiv","version":1}},"canonical_sha256":"6a0b83022e41085b7d4bc0c1832901c7079f2726a0e699f9d32fe1f0ed436fa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a0b83022e41085b7d4bc0c1832901c7079f2726a0e699f9d32fe1f0ed436fa0","first_computed_at":"2026-07-05T11:13:40.602516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:40.602516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5cSrD2EDL0uYpDmnq68AUdVAOR4dkZntstRXqoNa1oGr+4xbo9DK+iw+TPpzymAIZ99jnPHqmtsN5N4YmvOGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:40.603075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dfd9f40e47c82adbed39c5f608dc93b6a139c73e6f4766bfb323948608b32ca","sha256:971ce2dbcfe8060ac2911f52d03a7e706985c5081c71c8083c3141f3acfb969a"],"state_sha256":"4ebd30330577007b4bcf3c04e950ac01101adfe3a575d60cdcba5ff3bf9ec2c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"At4OlCoVcEXWjwINA2oirDBRI8zJiO0VZVf8Zb9EFJMN4Imsu8MG/CLpxrLzEMiYJ0XWFBcBgubWrFWsCF45Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:42:01.794478Z","bundle_sha256":"3b131e72ab6c49a793b3d719d0c7a13a059752010d1856a090f154ed486e7372"}}