{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JE5LMHLAQFFHZSKK3R5A6BVM7Y","short_pith_number":"pith:JE5LMHLA","canonical_record":{"source":{"id":"2506.12497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-14T13:17:47Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"37bda629804754f6e302a3d54ae06fcf3c57cb3f8bd7f53a6816bd3436eb1b05","abstract_canon_sha256":"df9db1ebe277b63d1f8da76c1a202769290f58560d693b58ac89df7469f0982b"},"schema_version":"1.0"},"canonical_sha256":"493ab61d60814a7cc94adc7a0f06acfe3cfee3367b551ec414b4c70bcd16bc06","source":{"kind":"arxiv","id":"2506.12497","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12497","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12497v2","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12497","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"JE5LMHLAQFFH","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"JE5LMHLAQFFHZSKK","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"JE5LMHLA","created_at":"2026-07-05T11:23:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JE5LMHLAQFFHZSKK3R5A6BVM7Y","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-14T13:17:47Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"37bda629804754f6e302a3d54ae06fcf3c57cb3f8bd7f53a6816bd3436eb1b05","abstract_canon_sha256":"df9db1ebe277b63d1f8da76c1a202769290f58560d693b58ac89df7469f0982b"},"schema_version":"1.0"},"canonical_sha256":"493ab61d60814a7cc94adc7a0f06acfe3cfee3367b551ec414b4c70bcd16bc06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:30.108902Z","signature_b64":"JIJ6DrA9NzSvZ6TAsfZIjI7o396w/5u9lBcd1jIwr5qAef6icFQhidqLTiOJHbGhRRk8k5Gjz9MmMJGL6tafDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"493ab61d60814a7cc94adc7a0f06acfe3cfee3367b551ec414b4c70bcd16bc06","last_reissued_at":"2026-07-05T11:23:30.108350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:30.108350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12497","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gjcAO/FNaL0zfqbD9bXv1pVc23Bo4nwyORcxl1NAR3fRN8umZlHNLvalaczY/09/wxtQYoNJ6CdrmlBK5aAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:01:54.590450Z"},"content_sha256":"779f5fd8bd816e215327f014e3f47540cdf816293f2c9787a3c41573f12a3c54","schema_version":"1.0","event_id":"sha256:779f5fd8bd816e215327f014e3f47540cdf816293f2c9787a3c41573f12a3c54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JE5LMHLAQFFHZSKK3R5A6BVM7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Ali Baheri","submitted_at":"2025-06-14T13:17:47Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) demands principled mechanisms to align heterogeneous policies while preserving the capacity for specialized behavior. We introduce a novel consensus framework that defines the team strategy as the entropic-regularized $p$-Wasserstein barycenter of agents' joint state--action visitation measures. By augmenting each agent's policy objective with a soft penalty proportional to its Sinkhorn divergence from this barycenter, the proposed approach encourages coherent group behavior without enforcing rigid parameter sharing. We derive an algorithm "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12497","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/2506.12497/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":"2026-07-05T11:23:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a72Mg8hBSwaIL7MDSDR9evkAGSo+ICdrbqv55KDedIbz6CxMckC4OzVTRwqJyHOJJkja1/WKcYeg830NOV74Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:01:54.591003Z"},"content_sha256":"0842e5f097637a203a6c735fb42d57f8f7d721ec9feab21ec12be084a4edd741","schema_version":"1.0","event_id":"sha256:0842e5f097637a203a6c735fb42d57f8f7d721ec9feab21ec12be084a4edd741"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y/bundle.json","state_url":"https://pith.science/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y/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":"2026-08-09T03:01:54Z","links":{"resolver":"https://pith.science/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y","bundle":"https://pith.science/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y/bundle.json","state":"https://pith.science/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JE5LMHLAQFFHZSKK3R5A6BVM7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JE5LMHLAQFFHZSKK3R5A6BVM7Y","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":"df9db1ebe277b63d1f8da76c1a202769290f58560d693b58ac89df7469f0982b","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-14T13:17:47Z","title_canon_sha256":"37bda629804754f6e302a3d54ae06fcf3c57cb3f8bd7f53a6816bd3436eb1b05"},"schema_version":"1.0","source":{"id":"2506.12497","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12497","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12497v2","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12497","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"JE5LMHLAQFFH","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"JE5LMHLAQFFHZSKK","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"JE5LMHLA","created_at":"2026-07-05T11:23:30Z"}],"graph_snapshots":[{"event_id":"sha256:0842e5f097637a203a6c735fb42d57f8f7d721ec9feab21ec12be084a4edd741","target":"graph","created_at":"2026-07-05T11:23:30Z","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/2506.12497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) demands principled mechanisms to align heterogeneous policies while preserving the capacity for specialized behavior. We introduce a novel consensus framework that defines the team strategy as the entropic-regularized $p$-Wasserstein barycenter of agents' joint state--action visitation measures. By augmenting each agent's policy objective with a soft penalty proportional to its Sinkhorn divergence from this barycenter, the proposed approach encourages coherent group behavior without enforcing rigid parameter sharing. We derive an algorithm ","authors_text":"Ali Baheri","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-14T13:17:47Z","title":"Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12497","kind":"arxiv","version":2},"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":"sha256:779f5fd8bd816e215327f014e3f47540cdf816293f2c9787a3c41573f12a3c54","target":"record","created_at":"2026-07-05T11:23:30Z","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":"df9db1ebe277b63d1f8da76c1a202769290f58560d693b58ac89df7469f0982b","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-14T13:17:47Z","title_canon_sha256":"37bda629804754f6e302a3d54ae06fcf3c57cb3f8bd7f53a6816bd3436eb1b05"},"schema_version":"1.0","source":{"id":"2506.12497","kind":"arxiv","version":2}},"canonical_sha256":"493ab61d60814a7cc94adc7a0f06acfe3cfee3367b551ec414b4c70bcd16bc06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"493ab61d60814a7cc94adc7a0f06acfe3cfee3367b551ec414b4c70bcd16bc06","first_computed_at":"2026-07-05T11:23:30.108350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:30.108350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JIJ6DrA9NzSvZ6TAsfZIjI7o396w/5u9lBcd1jIwr5qAef6icFQhidqLTiOJHbGhRRk8k5Gjz9MmMJGL6tafDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:30.108902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12497","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:779f5fd8bd816e215327f014e3f47540cdf816293f2c9787a3c41573f12a3c54","sha256:0842e5f097637a203a6c735fb42d57f8f7d721ec9feab21ec12be084a4edd741"],"state_sha256":"2d270094514f3d216bceeb16b7bf2c91895b2a30a72192461d0ea87c72f9a329"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R0S8rBhTLnrZ6Z2PrDNVB2s2idniTs/H0vuLpVfQTgasZ852JEPbNa3KDSI88blKiCD8tqDebu2fIcpLA6UNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:01:54.597157Z","bundle_sha256":"51adc70d80b7fe404e0a531a5f5aa4571048a207e5cccb52f16e691497ec2ee5"}}