{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WAOCKBLDLXFDCH5PXLT2JXU7WO","short_pith_number":"pith:WAOCKBLD","canonical_record":{"source":{"id":"2506.15825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T19:09:57Z","cross_cats_sorted":[],"title_canon_sha256":"0bccfd4f9c312269d73f1cde81710b295289a31e63136e254441bfa1c814d39f","abstract_canon_sha256":"f59e3805e7361065929a87effde02f3a43ca41837ebb8073cf088319f5ced085"},"schema_version":"1.0"},"canonical_sha256":"b01c2505635dca311fafbae7a4de9fb38f9c00df962c4ac5f8bd1f2e7d59796b","source":{"kind":"arxiv","id":"2506.15825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15825","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15825v1","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15825","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"pith_short_12","alias_value":"WAOCKBLDLXFD","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"pith_short_16","alias_value":"WAOCKBLDLXFDCH5P","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"pith_short_8","alias_value":"WAOCKBLD","created_at":"2026-07-05T11:23:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WAOCKBLDLXFDCH5PXLT2JXU7WO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.15825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T19:09:57Z","cross_cats_sorted":[],"title_canon_sha256":"0bccfd4f9c312269d73f1cde81710b295289a31e63136e254441bfa1c814d39f","abstract_canon_sha256":"f59e3805e7361065929a87effde02f3a43ca41837ebb8073cf088319f5ced085"},"schema_version":"1.0"},"canonical_sha256":"b01c2505635dca311fafbae7a4de9fb38f9c00df962c4ac5f8bd1f2e7d59796b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:52.998062Z","signature_b64":"w260Tqv7q9Im66HvdulKLMIAn4SHAZOiaJqOdCsv5drYwuBGk3t5rYNCTwxpEIUM2UbrXw0CWymegm3rN2ZkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b01c2505635dca311fafbae7a4de9fb38f9c00df962c4ac5f8bd1f2e7d59796b","last_reissued_at":"2026-07-05T11:23:52.997528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:52.997528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.15825","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":"2026-07-05T11:23:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"084ubMKTRLFuCmHWtfHXrUEYtcPOdpT9c7gZ/WATZITxPybqfHWqQVKC8s+pPMk1sMLRaXP2oa7c+6e2bDhjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:49:20.131705Z"},"content_sha256":"8a4f5ec8a05cb22d2fac665cb35d4ad0825aeb001fbbe3c67a74027ccd885ea7","schema_version":"1.0","event_id":"sha256:8a4f5ec8a05cb22d2fac665cb35d4ad0825aeb001fbbe3c67a74027ccd885ea7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WAOCKBLDLXFDCH5PXLT2JXU7WO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Luiz Pereira, M. Hadi Amini","submitted_at":"2025-06-18T19:09:57Z","abstract_excerpt":"In this paper, we first propose a novel algorithm for model fusion that leverages Wasserstein barycenters in training a global Deep Neural Network (DNN) in a distributed architecture. To this end, we divide the dataset into equal parts that are fed to \"agents\" who have identical deep neural networks and train only over the dataset fed to them (known as the local dataset). After some training iterations, we perform an aggregation step where we combine the weight parameters of all neural networks using Wasserstein barycenters. These steps form the proposed algorithm referred to as FedWB. Moreove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15825","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/2506.15825/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":"2026-07-05T11:23:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OetYgNaDOyHroPzEGhCYxcrpP7J2kVacem+qYEwF1/4S7cTv4SXSeAfehbhaod/Mc2r54R8tFDDrshqwlCm2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:49:20.132252Z"},"content_sha256":"5e03b8c61cc83c5605507aee458659fdf6507c4b37769cad89356b4c4933aa52","schema_version":"1.0","event_id":"sha256:5e03b8c61cc83c5605507aee458659fdf6507c4b37769cad89356b4c4933aa52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO/bundle.json","state_url":"https://pith.science/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO/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":"2026-08-08T05:49:20Z","links":{"resolver":"https://pith.science/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO","bundle":"https://pith.science/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO/bundle.json","state":"https://pith.science/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAOCKBLDLXFDCH5PXLT2JXU7WO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WAOCKBLDLXFDCH5PXLT2JXU7WO","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":"f59e3805e7361065929a87effde02f3a43ca41837ebb8073cf088319f5ced085","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T19:09:57Z","title_canon_sha256":"0bccfd4f9c312269d73f1cde81710b295289a31e63136e254441bfa1c814d39f"},"schema_version":"1.0","source":{"id":"2506.15825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15825","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15825v1","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15825","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"pith_short_12","alias_value":"WAOCKBLDLXFD","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"pith_short_16","alias_value":"WAOCKBLDLXFDCH5P","created_at":"2026-07-05T11:23:52Z"},{"alias_kind":"pith_short_8","alias_value":"WAOCKBLD","created_at":"2026-07-05T11:23:52Z"}],"graph_snapshots":[{"event_id":"sha256:5e03b8c61cc83c5605507aee458659fdf6507c4b37769cad89356b4c4933aa52","target":"graph","created_at":"2026-07-05T11:23:52Z","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/2506.15825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we first propose a novel algorithm for model fusion that leverages Wasserstein barycenters in training a global Deep Neural Network (DNN) in a distributed architecture. To this end, we divide the dataset into equal parts that are fed to \"agents\" who have identical deep neural networks and train only over the dataset fed to them (known as the local dataset). After some training iterations, we perform an aggregation step where we combine the weight parameters of all neural networks using Wasserstein barycenters. These steps form the proposed algorithm referred to as FedWB. Moreove","authors_text":"Luiz Pereira, M. Hadi Amini","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T19:09:57Z","title":"Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15825","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":"sha256:8a4f5ec8a05cb22d2fac665cb35d4ad0825aeb001fbbe3c67a74027ccd885ea7","target":"record","created_at":"2026-07-05T11:23:52Z","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":"f59e3805e7361065929a87effde02f3a43ca41837ebb8073cf088319f5ced085","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T19:09:57Z","title_canon_sha256":"0bccfd4f9c312269d73f1cde81710b295289a31e63136e254441bfa1c814d39f"},"schema_version":"1.0","source":{"id":"2506.15825","kind":"arxiv","version":1}},"canonical_sha256":"b01c2505635dca311fafbae7a4de9fb38f9c00df962c4ac5f8bd1f2e7d59796b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b01c2505635dca311fafbae7a4de9fb38f9c00df962c4ac5f8bd1f2e7d59796b","first_computed_at":"2026-07-05T11:23:52.997528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:52.997528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w260Tqv7q9Im66HvdulKLMIAn4SHAZOiaJqOdCsv5drYwuBGk3t5rYNCTwxpEIUM2UbrXw0CWymegm3rN2ZkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:52.998062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a4f5ec8a05cb22d2fac665cb35d4ad0825aeb001fbbe3c67a74027ccd885ea7","sha256:5e03b8c61cc83c5605507aee458659fdf6507c4b37769cad89356b4c4933aa52"],"state_sha256":"1b781a7f23cf4866233bbfba058cb9983120cadeeb89521a5c2be95be59fea7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Du/vELOIZA3ecoD1CpJrfJCuzaRdWHyn3CfMrGBwKapxKGeH2f3vOGFPPGN8t0B+7M0NsHJmiMJkSJO02IbBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:49:20.137033Z","bundle_sha256":"5e3a9c2aacaa73e132ff13293a0012ca808fbc06f560ee67135f0faed9b677ed"}}