{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5ITGTNJDXXTLYOBVZ7VEZ4MGG6","short_pith_number":"pith:5ITGTNJD","canonical_record":{"source":{"id":"2412.14555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T06:13:59Z","cross_cats_sorted":["cs.DC","cs.MA"],"title_canon_sha256":"245ab640fbe18bd278ea020d6fdb445b8da62784694f0c625423802a5d9e131c","abstract_canon_sha256":"fe516e9acd98203e0fbcdf6a66e3284f4dcd3ca5fe04d4ef2cb615aae378544c"},"schema_version":"1.0"},"canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","source":{"kind":"arxiv","id":"2412.14555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14555","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14555v1","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14555","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"pith_short_12","alias_value":"5ITGTNJDXXTL","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"pith_short_16","alias_value":"5ITGTNJDXXTLYOBV","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"pith_short_8","alias_value":"5ITGTNJD","created_at":"2026-07-05T09:53:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5ITGTNJDXXTLYOBVZ7VEZ4MGG6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T06:13:59Z","cross_cats_sorted":["cs.DC","cs.MA"],"title_canon_sha256":"245ab640fbe18bd278ea020d6fdb445b8da62784694f0c625423802a5d9e131c","abstract_canon_sha256":"fe516e9acd98203e0fbcdf6a66e3284f4dcd3ca5fe04d4ef2cb615aae378544c"},"schema_version":"1.0"},"canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:29.177157Z","signature_b64":"lNCyRMwSHZRYsVonW37YO2DHbfIA1uqbV5UsugyeD/E4yn8n/T0br/OeVyxVgQ/2lKMb1OSFgZ+gcSm85LozCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","last_reissued_at":"2026-07-05T09:53:29.176357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:29.176357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14555","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":"2026-07-05T09:53:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0o6SIoY5gWEVcgMcGsxEwJ2AB+Ua4MlLIBnyuP2G1EeqnB2DM8hSlfqchBEYQOnmF8uBOA/9jmO1pmxZQuevAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:59:03.368082Z"},"content_sha256":"2ad89b73a7932d7c0651e44f9d88c7c68fe78a0be52d037ef8f1aa0792c85433","schema_version":"1.0","event_id":"sha256:2ad89b73a7932d7c0651e44f9d88c7c68fe78a0be52d037ef8f1aa0792c85433"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5ITGTNJDXXTLYOBVZ7VEZ4MGG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Single-Loop Federated Actor-Critic across Heterogeneous Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Xiaowen Gong, Ye Zhu","submitted_at":"2024-12-19T06:13:59Z","abstract_excerpt":"Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL) algorithms, the actor-critic (AC) algorithm stands out for its low variance and high sample efficiency. However, little to nothing is known theoretically about AC in a federated manner, especially each agent interacts with a potentially different environment. The lack of such results is attributed to various technical challenges: a two-level structure illustrating "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14555","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/2412.14555/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":"2026-07-05T09:53:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/yOGRwluRDDZU5VpRglkoHuhGIHgtWp55txKRKeMTqlcGrpJtvP8tMQ3Qk7iOyMLE3X+BeSnd1LfSMpsRjhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:59:03.368886Z"},"content_sha256":"1f7ff3ccf5023cee5bd2e09030d8d6bbd88b3ca089fdf3dd05e04961b18360c6","schema_version":"1.0","event_id":"sha256:1f7ff3ccf5023cee5bd2e09030d8d6bbd88b3ca089fdf3dd05e04961b18360c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/bundle.json","state_url":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/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":"2026-08-17T13:59:03Z","links":{"resolver":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6","bundle":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/bundle.json","state":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5ITGTNJDXXTLYOBVZ7VEZ4MGG6","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":"fe516e9acd98203e0fbcdf6a66e3284f4dcd3ca5fe04d4ef2cb615aae378544c","cross_cats_sorted":["cs.DC","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T06:13:59Z","title_canon_sha256":"245ab640fbe18bd278ea020d6fdb445b8da62784694f0c625423802a5d9e131c"},"schema_version":"1.0","source":{"id":"2412.14555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14555","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14555v1","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14555","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"pith_short_12","alias_value":"5ITGTNJDXXTL","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"pith_short_16","alias_value":"5ITGTNJDXXTLYOBV","created_at":"2026-07-05T09:53:29Z"},{"alias_kind":"pith_short_8","alias_value":"5ITGTNJD","created_at":"2026-07-05T09:53:29Z"}],"graph_snapshots":[{"event_id":"sha256:1f7ff3ccf5023cee5bd2e09030d8d6bbd88b3ca089fdf3dd05e04961b18360c6","target":"graph","created_at":"2026-07-05T09:53:29Z","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/2412.14555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL) algorithms, the actor-critic (AC) algorithm stands out for its low variance and high sample efficiency. However, little to nothing is known theoretically about AC in a federated manner, especially each agent interacts with a potentially different environment. The lack of such results is attributed to various technical challenges: a two-level structure illustrating ","authors_text":"Xiaowen Gong, Ye Zhu","cross_cats":["cs.DC","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T06:13:59Z","title":"Single-Loop Federated Actor-Critic across Heterogeneous Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14555","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":"sha256:2ad89b73a7932d7c0651e44f9d88c7c68fe78a0be52d037ef8f1aa0792c85433","target":"record","created_at":"2026-07-05T09:53:29Z","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":"fe516e9acd98203e0fbcdf6a66e3284f4dcd3ca5fe04d4ef2cb615aae378544c","cross_cats_sorted":["cs.DC","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T06:13:59Z","title_canon_sha256":"245ab640fbe18bd278ea020d6fdb445b8da62784694f0c625423802a5d9e131c"},"schema_version":"1.0","source":{"id":"2412.14555","kind":"arxiv","version":1}},"canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","first_computed_at":"2026-07-05T09:53:29.176357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:29.176357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lNCyRMwSHZRYsVonW37YO2DHbfIA1uqbV5UsugyeD/E4yn8n/T0br/OeVyxVgQ/2lKMb1OSFgZ+gcSm85LozCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:29.177157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ad89b73a7932d7c0651e44f9d88c7c68fe78a0be52d037ef8f1aa0792c85433","sha256:1f7ff3ccf5023cee5bd2e09030d8d6bbd88b3ca089fdf3dd05e04961b18360c6"],"state_sha256":"24e80c504c05ef203aeb38ea96b433f52aa312acaf5c5bc7f72079142be05e72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+UT95CqCr170CJd6W3Al+gfGuoUdheH3cFjswEm9JZSkRMv6PCkxuNbPrNiHOZEEGRP3Dp068oJS64w+eaB4AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:59:03.377414Z","bundle_sha256":"d504d35934e5ea410ee87863939a186e5f445c33c4a58c76e8d0d5bb27209277"}}