{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6YZHSSCN7HXZXMQI7WCKUB53PQ","short_pith_number":"pith:6YZHSSCN","schema_version":"1.0","canonical_sha256":"f63279484df9ef9bb208fd84aa07bb7c2f9e997fb9e18752b1ffd711475b4717","source":{"kind":"arxiv","id":"2607.04170","version":1},"attestation_state":"computed","paper":{"title":"FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dandan Guo, Liyang Yuan, Yibo Yang","submitted_at":"2026-07-05T08:33:38Z","abstract_excerpt":"Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training. Sharpness-Aware Minimization (SAM) has emerged as a promising approach to improve generalization, yet its application in federated learning still suffers from divergence problems, since perturbations are computed locally and reflect client-specific loss geometries. To better understand this issue, we provide experimental evidence from a new perspective, the frequen"},"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":"2607.04170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T08:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"49ab67f8cafb47d48a75c88a1a70f288ecad6c6e39fcec54a6d143d8c67af776","abstract_canon_sha256":"4508bfefabe1313e44270eed65627677e8ef142e863d3491e48a30aa2aa51b8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:00.764113Z","signature_b64":"5fVYQgpiFdPUc8fKouzz36SKT1HwDGwgNvs6KtUrjCfwyD26utXI9TJ2kWWmSUb5PY2jV5bHFGrt+bGjMQSBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f63279484df9ef9bb208fd84aa07bb7c2f9e997fb9e18752b1ffd711475b4717","last_reissued_at":"2026-07-07T02:19:00.763348Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:00.763348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dandan Guo, Liyang Yuan, Yibo Yang","submitted_at":"2026-07-05T08:33:38Z","abstract_excerpt":"Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training. Sharpness-Aware Minimization (SAM) has emerged as a promising approach to improve generalization, yet its application in federated learning still suffers from divergence problems, since perturbations are computed locally and reflect client-specific loss geometries. To better understand this issue, we provide experimental evidence from a new perspective, the frequen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04170","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/2607.04170/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":"2607.04170","created_at":"2026-07-07T02:19:00.763470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04170v1","created_at":"2026-07-07T02:19:00.763470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04170","created_at":"2026-07-07T02:19:00.763470+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YZHSSCN7HXZ","created_at":"2026-07-07T02:19:00.763470+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YZHSSCN7HXZXMQI","created_at":"2026-07-07T02:19:00.763470+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YZHSSCN","created_at":"2026-07-07T02:19:00.763470+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/6YZHSSCN7HXZXMQI7WCKUB53PQ","json":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ.json","graph_json":"https://pith.science/api/pith-number/6YZHSSCN7HXZXMQI7WCKUB53PQ/graph.json","events_json":"https://pith.science/api/pith-number/6YZHSSCN7HXZXMQI7WCKUB53PQ/events.json","paper":"https://pith.science/paper/6YZHSSCN"},"agent_actions":{"view_html":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ","download_json":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ.json","view_paper":"https://pith.science/paper/6YZHSSCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04170&json=true","fetch_graph":"https://pith.science/api/pith-number/6YZHSSCN7HXZXMQI7WCKUB53PQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6YZHSSCN7HXZXMQI7WCKUB53PQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ/action/storage_attestation","attest_author":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ/action/author_attestation","sign_citation":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ/action/citation_signature","submit_replication":"https://pith.science/pith/6YZHSSCN7HXZXMQI7WCKUB53PQ/action/replication_record"}},"created_at":"2026-07-07T02:19:00.763470+00:00","updated_at":"2026-07-07T02:19:00.763470+00:00"}