{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WE5X327LDAO5MCSB3OLZ5GS6EN","short_pith_number":"pith:WE5X327L","canonical_record":{"source":{"id":"2506.01261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T02:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"b7e135bdebb354f550f88c1c17b49c77313a5571128d12692525a093b0fa294f","abstract_canon_sha256":"a5ee54f6ece799b0acebb6176bcda11d8976419292019504c44eb7bd49a7dc65"},"schema_version":"1.0"},"canonical_sha256":"b13b7debeb181dd60a41db979e9a5e23499ff487dc92a7bf99abb5a8514abe63","source":{"kind":"arxiv","id":"2506.01261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01261","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01261v1","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01261","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_12","alias_value":"WE5X327LDAO5","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_16","alias_value":"WE5X327LDAO5MCSB","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_8","alias_value":"WE5X327L","created_at":"2026-07-05T11:14:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WE5X327LDAO5MCSB3OLZ5GS6EN","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T02:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"b7e135bdebb354f550f88c1c17b49c77313a5571128d12692525a093b0fa294f","abstract_canon_sha256":"a5ee54f6ece799b0acebb6176bcda11d8976419292019504c44eb7bd49a7dc65"},"schema_version":"1.0"},"canonical_sha256":"b13b7debeb181dd60a41db979e9a5e23499ff487dc92a7bf99abb5a8514abe63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:10.770609Z","signature_b64":"kjOSVbQR5yIoy7KwhbSMPwvVhsOiwEAQvsJILwi+842GL7wQ33QQjxK3vs+gBIN1Fu5SxIIXOFLfTLKXa9JfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13b7debeb181dd60a41db979e9a5e23499ff487dc92a7bf99abb5a8514abe63","last_reissued_at":"2026-07-05T11:14:10.770110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:10.770110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01261","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":"2026-07-05T11:14:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n/U+pXNEySZFBMwDmvcdwZJ6gewSFNzbP0NLHRBA9wVD3XyaDKlN2pNL6s/zNPAn/TdvKNypPLa2FFpBy/fqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:32:18.021082Z"},"content_sha256":"57b083f2f68b7c62d6fac295add18695cccc0b451f628c86ff5c483ed72c86ea","schema_version":"1.0","event_id":"sha256:57b083f2f68b7c62d6fac295add18695cccc0b451f628c86ff5c483ed72c86ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WE5X327LDAO5MCSB3OLZ5GS6EN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shenghui Song, Zhijie Xie","submitted_at":"2025-06-02T02:20:22Z","abstract_excerpt":"In the context of Federated Reinforcement Learning (FRL), applying Proximal Policy Optimization (PPO) faces challenges related to the update order of its actor and critic due to the aggregation step occurring between successive iterations. In particular, when local actors are updated based on local critic estimations, the algorithm becomes vulnerable to data heterogeneity. As a result, the conventional update order in PPO (critic first, then actor) may cause heterogeneous gradient directions among clients, hindering convergence to a globally optimal policy. To address this issue, we propose Fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01261","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/2506.01261/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":"2026-07-05T11:14:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mT6X+A7PaelecKYlHbV8WjIxvuCZNcmHdFwQjh0OZMGF3d8jEV+bxmyOPUkca9ISKU9zt+qp9D72kkSuxdpVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:32:18.021420Z"},"content_sha256":"304d50c49e3148613eba1e9d5786149ef972337eb0a16287e0b2a422fb15fbf0","schema_version":"1.0","event_id":"sha256:304d50c49e3148613eba1e9d5786149ef972337eb0a16287e0b2a422fb15fbf0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WE5X327LDAO5MCSB3OLZ5GS6EN/bundle.json","state_url":"https://pith.science/pith/WE5X327LDAO5MCSB3OLZ5GS6EN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WE5X327LDAO5MCSB3OLZ5GS6EN/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":"2026-08-06T02:32:18Z","links":{"resolver":"https://pith.science/pith/WE5X327LDAO5MCSB3OLZ5GS6EN","bundle":"https://pith.science/pith/WE5X327LDAO5MCSB3OLZ5GS6EN/bundle.json","state":"https://pith.science/pith/WE5X327LDAO5MCSB3OLZ5GS6EN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WE5X327LDAO5MCSB3OLZ5GS6EN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WE5X327LDAO5MCSB3OLZ5GS6EN","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":"a5ee54f6ece799b0acebb6176bcda11d8976419292019504c44eb7bd49a7dc65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T02:20:22Z","title_canon_sha256":"b7e135bdebb354f550f88c1c17b49c77313a5571128d12692525a093b0fa294f"},"schema_version":"1.0","source":{"id":"2506.01261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01261","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01261v1","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01261","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_12","alias_value":"WE5X327LDAO5","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_16","alias_value":"WE5X327LDAO5MCSB","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_8","alias_value":"WE5X327L","created_at":"2026-07-05T11:14:10Z"}],"graph_snapshots":[{"event_id":"sha256:304d50c49e3148613eba1e9d5786149ef972337eb0a16287e0b2a422fb15fbf0","target":"graph","created_at":"2026-07-05T11:14:10Z","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/2506.01261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of Federated Reinforcement Learning (FRL), applying Proximal Policy Optimization (PPO) faces challenges related to the update order of its actor and critic due to the aggregation step occurring between successive iterations. In particular, when local actors are updated based on local critic estimations, the algorithm becomes vulnerable to data heterogeneity. As a result, the conventional update order in PPO (critic first, then actor) may cause heterogeneous gradient directions among clients, hindering convergence to a globally optimal policy. To address this issue, we propose Fe","authors_text":"Shenghui Song, Zhijie Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T02:20:22Z","title":"The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01261","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":"sha256:57b083f2f68b7c62d6fac295add18695cccc0b451f628c86ff5c483ed72c86ea","target":"record","created_at":"2026-07-05T11:14:10Z","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":"a5ee54f6ece799b0acebb6176bcda11d8976419292019504c44eb7bd49a7dc65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T02:20:22Z","title_canon_sha256":"b7e135bdebb354f550f88c1c17b49c77313a5571128d12692525a093b0fa294f"},"schema_version":"1.0","source":{"id":"2506.01261","kind":"arxiv","version":1}},"canonical_sha256":"b13b7debeb181dd60a41db979e9a5e23499ff487dc92a7bf99abb5a8514abe63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b13b7debeb181dd60a41db979e9a5e23499ff487dc92a7bf99abb5a8514abe63","first_computed_at":"2026-07-05T11:14:10.770110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:10.770110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kjOSVbQR5yIoy7KwhbSMPwvVhsOiwEAQvsJILwi+842GL7wQ33QQjxK3vs+gBIN1Fu5SxIIXOFLfTLKXa9JfBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:10.770609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57b083f2f68b7c62d6fac295add18695cccc0b451f628c86ff5c483ed72c86ea","sha256:304d50c49e3148613eba1e9d5786149ef972337eb0a16287e0b2a422fb15fbf0"],"state_sha256":"8aa8dcb9b093f572a0ffc87f0adbe67f40d3ee6acca42839aa85d628591b65be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d+LzmBIffjnrJarXnOa9feE3KsEP029GOBjpxUZedf9MTOsu42PHdekBl5DLRPTYwlJBBsPZ3Lu/VlD4dJ0uAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:32:18.025112Z","bundle_sha256":"c05c3b525700effdbb48615355c773581f14ad32ec7546a5dc168e9f81055f43"}}