{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NXPPQGOHCLBOLBCYGXXFWDDP5D","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":"24f6e76c0becceb6afb1c32862830ca6748a356eef6646e1cf91c15b186a4597","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T18:44:08Z","title_canon_sha256":"c533e2a89cb1531d688ad0ac55602f879d2f2ac22a73cb2e0ee5520833283eca"},"schema_version":"1.0","source":{"id":"2502.00870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00870","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00870v1","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00870","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"NXPPQGOHCLBO","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"NXPPQGOHCLBOLBCY","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"NXPPQGOH","created_at":"2026-07-05T10:08:39Z"}],"graph_snapshots":[{"event_id":"sha256:0ae137f5a1b2bd630b171fc62d55986e5674d6dcf55877b15ed73ecb46108ee5","target":"graph","created_at":"2026-07-05T10:08:39Z","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/2502.00870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Reinforcement Learning (FedRL) improves sample efficiency while preserving privacy; however, most existing studies assume homogeneous agents, limiting its applicability in real-world scenarios. This paper investigates FedRL in black-box settings with heterogeneous agents, where each agent employs distinct policy networks and training configurations without disclosing their internal details. Knowledge Distillation (KD) is a promising method for facilitating knowledge sharing among heterogeneous models, but it faces challenges related to the scarcity of public datasets and limitations ","authors_text":"Cheston Tan, Flint Xiaofeng Fan, Ji Wang, Weidong Bao, Wenzheng Jiang, Xiongtao Zhang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T18:44:08Z","title":"FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00870","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":"sha256:477126a7c5b1341061c09cde42ac22242a5d05973a605d651c61111fa29028d6","target":"record","created_at":"2026-07-05T10:08:39Z","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":"24f6e76c0becceb6afb1c32862830ca6748a356eef6646e1cf91c15b186a4597","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T18:44:08Z","title_canon_sha256":"c533e2a89cb1531d688ad0ac55602f879d2f2ac22a73cb2e0ee5520833283eca"},"schema_version":"1.0","source":{"id":"2502.00870","kind":"arxiv","version":1}},"canonical_sha256":"6ddef819c712c2e5845835ee5b0c6fe8e8a6499848db34b696c36067fb4bf397","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ddef819c712c2e5845835ee5b0c6fe8e8a6499848db34b696c36067fb4bf397","first_computed_at":"2026-07-05T10:08:39.397366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:39.397366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Fthoi5xXVfHWgsiY/eHcn0D25a1SVrHIww5r0swTYfHvplzQmRB8aJudH1PnBKpKLWGjHFrZbkIPyEAw3AGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:39.397734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:477126a7c5b1341061c09cde42ac22242a5d05973a605d651c61111fa29028d6","sha256:0ae137f5a1b2bd630b171fc62d55986e5674d6dcf55877b15ed73ecb46108ee5"],"state_sha256":"ead366379fad32335132fdf024d1de2fc40c127b069d162da152293a7eb2781f"}