{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LS46N7JBKESYA3BSLWWI6OSXPM","short_pith_number":"pith:LS46N7JB","schema_version":"1.0","canonical_sha256":"5cb9e6fd215125806c325dac8f3a577b1c198a4130f3aa71c91a76658875c6db","source":{"kind":"arxiv","id":"2505.09959","version":1},"attestation_state":"computed","paper":{"title":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bohui An, Zengxia Guo, Zhongqi Lu","submitted_at":"2025-05-15T04:41:21Z","abstract_excerpt":"Federated reinforcement learning (FRL) methods usually share the encrypted local state or policy information and help each client to learn from others while preserving everyone's privacy. In this work, we propose that sharing the approximated behavior metric-based state projection function is a promising way to enhance the performance of FRL and concurrently provides an effective protection of sensitive information. We introduce FedRAG, a FRL framework to learn a computationally practical projection function of states for each client and aggregating the parameters of projection functions at a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.09959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T04:41:21Z","cross_cats_sorted":[],"title_canon_sha256":"ccee57d0f4e891257c37acaef10f3dfa6055e8d677992d387b31442d6e90dd78","abstract_canon_sha256":"643d85efa39e39f471c12771c3b18823abcea28a3b31e9593d293f576f3171bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:31.129702Z","signature_b64":"FAq82bxfLrMptRnJvKOOzKRlp04rTOHCTI3EBsUdgm+WXeAUNiM3iA3o7rbBbc68lN15r+o+UPsqbbp6n0+hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb9e6fd215125806c325dac8f3a577b1c198a4130f3aa71c91a76658875c6db","last_reissued_at":"2026-07-05T11:03:31.129234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:31.129234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bohui An, Zengxia Guo, Zhongqi Lu","submitted_at":"2025-05-15T04:41:21Z","abstract_excerpt":"Federated reinforcement learning (FRL) methods usually share the encrypted local state or policy information and help each client to learn from others while preserving everyone's privacy. In this work, we propose that sharing the approximated behavior metric-based state projection function is a promising way to enhance the performance of FRL and concurrently provides an effective protection of sensitive information. We introduce FedRAG, a FRL framework to learn a computationally practical projection function of states for each client and aggregating the parameters of projection functions at a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09959","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/2505.09959/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.09959","created_at":"2026-07-05T11:03:31.129291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09959v1","created_at":"2026-07-05T11:03:31.129291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09959","created_at":"2026-07-05T11:03:31.129291+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS46N7JBKESY","created_at":"2026-07-05T11:03:31.129291+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS46N7JBKESYA3BS","created_at":"2026-07-05T11:03:31.129291+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS46N7JB","created_at":"2026-07-05T11:03:31.129291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM","json":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM.json","graph_json":"https://pith.science/api/pith-number/LS46N7JBKESYA3BSLWWI6OSXPM/graph.json","events_json":"https://pith.science/api/pith-number/LS46N7JBKESYA3BSLWWI6OSXPM/events.json","paper":"https://pith.science/paper/LS46N7JB"},"agent_actions":{"view_html":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM","download_json":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM.json","view_paper":"https://pith.science/paper/LS46N7JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09959&json=true","fetch_graph":"https://pith.science/api/pith-number/LS46N7JBKESYA3BSLWWI6OSXPM/graph.json","fetch_events":"https://pith.science/api/pith-number/LS46N7JBKESYA3BSLWWI6OSXPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM/action/storage_attestation","attest_author":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM/action/author_attestation","sign_citation":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM/action/citation_signature","submit_replication":"https://pith.science/pith/LS46N7JBKESYA3BSLWWI6OSXPM/action/replication_record"}},"created_at":"2026-07-05T11:03:31.129291+00:00","updated_at":"2026-07-05T11:03:31.129291+00:00"}