{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ELLRM2455Z6RXC6XBXPZT4BAYR","short_pith_number":"pith:ELLRM245","schema_version":"1.0","canonical_sha256":"22d7166b9dee7d1b8bd70ddf99f020c4574e9f2a46c9cc8c38448649d3b2f786","source":{"kind":"arxiv","id":"2605.27900","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lechao Cheng, Xiaohua Xu, Yuting Ma","submitted_at":"2026-05-27T03:21:49Z","abstract_excerpt":"Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising paradigm for various downstream tasks. By leveraging its strong representations, recent studies improve task adaptation under insufficient local data while preserving generalization. However, these methods emphasize fully local optimization with simple parameter aggregation,which can amplify inter-client optimization inconsistency and intra-client over-specialization under heterogeneous and full-data FL settings, making it difficult to balance global task adaptation and generalization. To address "},"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":"2605.27900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T03:21:49Z","cross_cats_sorted":[],"title_canon_sha256":"78c918bff923bd7d672c394675a2c5f9b149d0520f9faf1399cd05444209698b","abstract_canon_sha256":"cbc3f290b34f4d2289650bd645f8c135b2308f143ddf1600883eb074509b46e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:51.864441Z","signature_b64":"fbNweyAvpvceb9dnlwkVq6Vr+hghoec3XYlJWxbsK05urJGRkJAzM0uC7Ugt154BV8uLchqQ7qIKF3sx6S/7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22d7166b9dee7d1b8bd70ddf99f020c4574e9f2a46c9cc8c38448649d3b2f786","last_reissued_at":"2026-05-28T01:04:51.864044Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:51.864044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lechao Cheng, Xiaohua Xu, Yuting Ma","submitted_at":"2026-05-27T03:21:49Z","abstract_excerpt":"Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising paradigm for various downstream tasks. By leveraging its strong representations, recent studies improve task adaptation under insufficient local data while preserving generalization. However, these methods emphasize fully local optimization with simple parameter aggregation,which can amplify inter-client optimization inconsistency and intra-client over-specialization under heterogeneous and full-data FL settings, making it difficult to balance global task adaptation and generalization. To address "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27900","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/2605.27900/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":"2605.27900","created_at":"2026-05-28T01:04:51.864093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27900v1","created_at":"2026-05-28T01:04:51.864093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27900","created_at":"2026-05-28T01:04:51.864093+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELLRM2455Z6R","created_at":"2026-05-28T01:04:51.864093+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELLRM2455Z6RXC6X","created_at":"2026-05-28T01:04:51.864093+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELLRM245","created_at":"2026-05-28T01:04:51.864093+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/ELLRM2455Z6RXC6XBXPZT4BAYR","json":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR.json","graph_json":"https://pith.science/api/pith-number/ELLRM2455Z6RXC6XBXPZT4BAYR/graph.json","events_json":"https://pith.science/api/pith-number/ELLRM2455Z6RXC6XBXPZT4BAYR/events.json","paper":"https://pith.science/paper/ELLRM245"},"agent_actions":{"view_html":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR","download_json":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR.json","view_paper":"https://pith.science/paper/ELLRM245","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27900&json=true","fetch_graph":"https://pith.science/api/pith-number/ELLRM2455Z6RXC6XBXPZT4BAYR/graph.json","fetch_events":"https://pith.science/api/pith-number/ELLRM2455Z6RXC6XBXPZT4BAYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR/action/storage_attestation","attest_author":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR/action/author_attestation","sign_citation":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR/action/citation_signature","submit_replication":"https://pith.science/pith/ELLRM2455Z6RXC6XBXPZT4BAYR/action/replication_record"}},"created_at":"2026-05-28T01:04:51.864093+00:00","updated_at":"2026-05-28T01:04:51.864093+00:00"}