{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AKAWCDQQJ4KCXJ7UZAPFIY4GMF","short_pith_number":"pith:AKAWCDQQ","schema_version":"1.0","canonical_sha256":"0281610e104f142ba7f4c81e54638661523ae1136fb1fbc4408f399a3703c839","source":{"kind":"arxiv","id":"2605.16350","version":1},"attestation_state":"computed","paper":{"title":"Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Lin, Han Yu, Hong Chen, Peilin Zhao, Pengcheng Wu, Xiuze Zhou, Yuanguo Lin","submitted_at":"2026-05-08T04:31:46Z","abstract_excerpt":"We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules, not just static models, to tackle Non-IID client data. To address this, we propose Federated Nested Learning (FedNL), a novel framework that reformulates FL as a three-level nested optimization system. FedNL embeds Titans-based linear attention into FL, enabling clients to perform lightweight, zero-shot test-time adaptation by treating a delta rule as an online gradient step. Experiments on Non-IID MMLU and long-context benchmarks show that FedNL"},"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":"2605.16350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T04:31:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd9b1870b0c89f1303fb326fda6c4da45aa4fb0f885cede1687652bf9a2a2880","abstract_canon_sha256":"157e39a91f779f4a242d1dc42d89741ecf3f31d81d287e3384563cb5990569f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:17.901722Z","signature_b64":"gYtQ207vBgjtHna0l0HLWEWhELN1o9MwZKOoWlanXnJIcj3ypM+rmBAw18qgaIIkP7w+Xj/fau9IfGNmKpfpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0281610e104f142ba7f4c81e54638661523ae1136fb1fbc4408f399a3703c839","last_reissued_at":"2026-05-20T00:02:17.901120Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:17.901120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Lin, Han Yu, Hong Chen, Peilin Zhao, Pengcheng Wu, Xiuze Zhou, Yuanguo Lin","submitted_at":"2026-05-08T04:31:46Z","abstract_excerpt":"We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules, not just static models, to tackle Non-IID client data. To address this, we propose Federated Nested Learning (FedNL), a novel framework that reformulates FL as a three-level nested optimization system. FedNL embeds Titans-based linear attention into FL, enabling clients to perform lightweight, zero-shot test-time adaptation by treating a delta rule as an online gradient step. Experiments on Non-IID MMLU and long-context benchmarks show that FedNL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16350","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/2605.16350/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":"2605.16350","created_at":"2026-05-20T00:02:17.901205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16350v1","created_at":"2026-05-20T00:02:17.901205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16350","created_at":"2026-05-20T00:02:17.901205+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKAWCDQQJ4KC","created_at":"2026-05-20T00:02:17.901205+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKAWCDQQJ4KCXJ7U","created_at":"2026-05-20T00:02:17.901205+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKAWCDQQ","created_at":"2026-05-20T00:02:17.901205+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/AKAWCDQQJ4KCXJ7UZAPFIY4GMF","json":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF.json","graph_json":"https://pith.science/api/pith-number/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/graph.json","events_json":"https://pith.science/api/pith-number/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/events.json","paper":"https://pith.science/paper/AKAWCDQQ"},"agent_actions":{"view_html":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF","download_json":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF.json","view_paper":"https://pith.science/paper/AKAWCDQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16350&json=true","fetch_graph":"https://pith.science/api/pith-number/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/graph.json","fetch_events":"https://pith.science/api/pith-number/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/action/storage_attestation","attest_author":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/action/author_attestation","sign_citation":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/action/citation_signature","submit_replication":"https://pith.science/pith/AKAWCDQQJ4KCXJ7UZAPFIY4GMF/action/replication_record"}},"created_at":"2026-05-20T00:02:17.901205+00:00","updated_at":"2026-05-20T00:02:17.901205+00:00"}