{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VASH26KQT3MHDNAJO3OE5UWSWZ","short_pith_number":"pith:VASH26KQ","schema_version":"1.0","canonical_sha256":"a8247d79509ed871b40976dc4ed2d2b64c906d084d9029752533aafff53b2d60","source":{"kind":"arxiv","id":"2503.15111","version":2},"attestation_state":"computed","paper":{"title":"FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changlong Shi, Dandan Guo, He Zhao, Jinmeng Li, Yi Chang","submitted_at":"2025-03-19T11:10:28Z","abstract_excerpt":"In Federated Learning (FL), weighted aggregation of local models is conducted to generate a new global model, and the aggregation weights are typically normalized to 1. A recent study identifies the global weight shrinking effect in FL, indicating an enhancement in the global model's generalization when the sum of weights (i.e., the shrinking factor) is smaller than 1, where how to learn the shrinking factor becomes crucial. However, principled approaches to this solution have not been carefully studied from the adequate consideration of privacy concerns and layer-wise distinctions. To this en"},"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":"2503.15111","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T11:10:28Z","cross_cats_sorted":[],"title_canon_sha256":"ba264a7c0c901b2ea04538f12948aa9f59efe93f288b0ba48101c7a20dc7de93","abstract_canon_sha256":"687ac1ef77c9985c1af8c57ab8c753dd997ef2060aef897cb19a93bdc352f042"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:41.010451Z","signature_b64":"Qe6s/qLbSUthrBHRTIFNBM7d5C13Hfr3bzgmgzg15BCloVjRmtddiw0GzY2geZbxSgmZDk3PBOCRjeI2ANOEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8247d79509ed871b40976dc4ed2d2b64c906d084d9029752533aafff53b2d60","last_reissued_at":"2026-07-05T10:40:41.009902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:41.009902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changlong Shi, Dandan Guo, He Zhao, Jinmeng Li, Yi Chang","submitted_at":"2025-03-19T11:10:28Z","abstract_excerpt":"In Federated Learning (FL), weighted aggregation of local models is conducted to generate a new global model, and the aggregation weights are typically normalized to 1. A recent study identifies the global weight shrinking effect in FL, indicating an enhancement in the global model's generalization when the sum of weights (i.e., the shrinking factor) is smaller than 1, where how to learn the shrinking factor becomes crucial. However, principled approaches to this solution have not been carefully studied from the adequate consideration of privacy concerns and layer-wise distinctions. To this en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15111","kind":"arxiv","version":2},"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/2503.15111/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":"2503.15111","created_at":"2026-07-05T10:40:41.009963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15111v2","created_at":"2026-07-05T10:40:41.009963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15111","created_at":"2026-07-05T10:40:41.009963+00:00"},{"alias_kind":"pith_short_12","alias_value":"VASH26KQT3MH","created_at":"2026-07-05T10:40:41.009963+00:00"},{"alias_kind":"pith_short_16","alias_value":"VASH26KQT3MHDNAJ","created_at":"2026-07-05T10:40:41.009963+00:00"},{"alias_kind":"pith_short_8","alias_value":"VASH26KQ","created_at":"2026-07-05T10:40:41.009963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09208","citing_title":"FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ","json":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ.json","graph_json":"https://pith.science/api/pith-number/VASH26KQT3MHDNAJO3OE5UWSWZ/graph.json","events_json":"https://pith.science/api/pith-number/VASH26KQT3MHDNAJO3OE5UWSWZ/events.json","paper":"https://pith.science/paper/VASH26KQ"},"agent_actions":{"view_html":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ","download_json":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ.json","view_paper":"https://pith.science/paper/VASH26KQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15111&json=true","fetch_graph":"https://pith.science/api/pith-number/VASH26KQT3MHDNAJO3OE5UWSWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VASH26KQT3MHDNAJO3OE5UWSWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ/action/storage_attestation","attest_author":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ/action/author_attestation","sign_citation":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ/action/citation_signature","submit_replication":"https://pith.science/pith/VASH26KQT3MHDNAJO3OE5UWSWZ/action/replication_record"}},"created_at":"2026-07-05T10:40:41.009963+00:00","updated_at":"2026-07-05T10:40:41.009963+00:00"}