{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K6Z7S77557JUQAVHFWOEJ7IJTP","short_pith_number":"pith:K6Z7S775","schema_version":"1.0","canonical_sha256":"57b3f97ffdefd34802a72d9c44fd099bde484e78b6bce320c98631c768bbb4ff","source":{"kind":"arxiv","id":"2601.09166","version":3},"attestation_state":"computed","paper":{"title":"DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Mrinmay Sen, Sayantan Banerjee, Sidhant Nair, Tanmay Sen","submitted_at":"2026-01-14T05:11:28Z","abstract_excerpt":"Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradient quality. Although second-order optimization can accelerate training, existing approaches for DP-FL face significant scalability limitations: Newton-type methods require clients to compute Hessians, while feature covariance methods scale poorly with model dimension. We propose DP-FedSOFIM, a simple and scalable Hessian approximation-based second-order optimization method for DP-FL. The method constructs a regulari"},"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":"2601.09166","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-14T05:11:28Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"f7d17822b618a945338dc5c9f6659c8bc2b22d8b6d4a0aa6d15080c419a37c28","abstract_canon_sha256":"586d032624b995227e2c8e39e49f11a0b111a4727e22819f074c880a06b5a236"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:45.890739Z","signature_b64":"SUe/DNrZXWlIRB8IiM1za6jHluWOQp9XDoBrdX4S2kslM6YGhXtWVb30GhBeNS82rsu61Amh6NrxF9/dZHROCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57b3f97ffdefd34802a72d9c44fd099bde484e78b6bce320c98631c768bbb4ff","last_reissued_at":"2026-06-23T02:12:45.890193Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:45.890193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Mrinmay Sen, Sayantan Banerjee, Sidhant Nair, Tanmay Sen","submitted_at":"2026-01-14T05:11:28Z","abstract_excerpt":"Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradient quality. Although second-order optimization can accelerate training, existing approaches for DP-FL face significant scalability limitations: Newton-type methods require clients to compute Hessians, while feature covariance methods scale poorly with model dimension. We propose DP-FedSOFIM, a simple and scalable Hessian approximation-based second-order optimization method for DP-FL. The method constructs a regulari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09166","kind":"arxiv","version":3},"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/2601.09166/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":"2601.09166","created_at":"2026-06-23T02:12:45.890268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.09166v3","created_at":"2026-06-23T02:12:45.890268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09166","created_at":"2026-06-23T02:12:45.890268+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6Z7S77557JU","created_at":"2026-06-23T02:12:45.890268+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6Z7S77557JUQAVH","created_at":"2026-06-23T02:12:45.890268+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6Z7S775","created_at":"2026-06-23T02:12:45.890268+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/K6Z7S77557JUQAVHFWOEJ7IJTP","json":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP.json","graph_json":"https://pith.science/api/pith-number/K6Z7S77557JUQAVHFWOEJ7IJTP/graph.json","events_json":"https://pith.science/api/pith-number/K6Z7S77557JUQAVHFWOEJ7IJTP/events.json","paper":"https://pith.science/paper/K6Z7S775"},"agent_actions":{"view_html":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP","download_json":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP.json","view_paper":"https://pith.science/paper/K6Z7S775","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.09166&json=true","fetch_graph":"https://pith.science/api/pith-number/K6Z7S77557JUQAVHFWOEJ7IJTP/graph.json","fetch_events":"https://pith.science/api/pith-number/K6Z7S77557JUQAVHFWOEJ7IJTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP/action/storage_attestation","attest_author":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP/action/author_attestation","sign_citation":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP/action/citation_signature","submit_replication":"https://pith.science/pith/K6Z7S77557JUQAVHFWOEJ7IJTP/action/replication_record"}},"created_at":"2026-06-23T02:12:45.890268+00:00","updated_at":"2026-06-23T02:12:45.890268+00:00"}