{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DI6LSVBK6EQ4EBYNDIDENOIXFX","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":"b1f4578394f74d785d83a93d6c4e50c2cdabc2038a0f0f4fb2f55fefb47452cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:32:32Z","title_canon_sha256":"0a89817ca8dcc5f460009426e0c5f1b1d168c275f32215c65ad81693d18afe42"},"schema_version":"1.0","source":{"id":"2606.03094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03094","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03094v1","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03094","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"DI6LSVBK6EQ4","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"DI6LSVBK6EQ4EBYN","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"DI6LSVBK","created_at":"2026-06-03T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:1efcad4aa8c574dc2c691ccff47ae59c76f5fd384612f9966519b2feba490759","target":"graph","created_at":"2026-06-03T01:05:31Z","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/2606.03094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language models have established reinforcement learning as the primary paradigm for eliciting self-correction and long-chain reasoning. While group relative policy optimization (GRPO) offers superior scalability by eliminating the critic network, deploying it on a central infrastructure entails collecting a large volume of data from distributed owners, which poses significant privacy risks. To address these concerns, we introduce federated GRPO (FGRPO), a framework designed to decentralize the fine-tuning of reasoning models across heterogeneous data owners. To effectively m","authors_text":"Feng Li, Jun Luo, Kai Han, Kai Wang, Pengyu Chen, Shaowei Li, Yunsheng Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:32:32Z","title":"FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03094","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":"sha256:95a1cc83d24f349e107619f4b0d4988fc9df715fc92ae23eb38f0904f8626dd9","target":"record","created_at":"2026-06-03T01:05:31Z","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":"b1f4578394f74d785d83a93d6c4e50c2cdabc2038a0f0f4fb2f55fefb47452cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:32:32Z","title_canon_sha256":"0a89817ca8dcc5f460009426e0c5f1b1d168c275f32215c65ad81693d18afe42"},"schema_version":"1.0","source":{"id":"2606.03094","kind":"arxiv","version":1}},"canonical_sha256":"1a3cb9542af121c2070d1a0646b9172dca7971015450b39487dad57e9289f4cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a3cb9542af121c2070d1a0646b9172dca7971015450b39487dad57e9289f4cd","first_computed_at":"2026-06-03T01:05:31.492780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:31.492780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z/RFLInI4Y84aX6keY+3ICFZpVgdinCmfO1NP6jP9d+mHnxcivjnsBNorD8Zcf54cbOB7RHp0fx2z7qD0WfcAw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:31.493185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03094","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95a1cc83d24f349e107619f4b0d4988fc9df715fc92ae23eb38f0904f8626dd9","sha256:1efcad4aa8c574dc2c691ccff47ae59c76f5fd384612f9966519b2feba490759"],"state_sha256":"37f530b52d624ae4edd07d697341c2ce007ea5f3683ff5bfb15213d3860d1720"}