{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7IQ5JRGYTXQXPMIOBSF5K3RTS","short_pith_number":"pith:V7IQ5JRG","schema_version":"1.0","canonical_sha256":"afd10ea626c4ef0bbd8870645eab719c8d500c928ca41f4fb7f9e0ee489b4621","source":{"kind":"arxiv","id":"2411.16478","version":2},"attestation_state":"computed","paper":{"title":"Distributed, communication-efficient, and differentially private estimation of KL divergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Carsten Maple, Graham Cormode, Mary Scott, Sayan Biswas","submitted_at":"2024-11-25T15:20:40Z","abstract_excerpt":"A key task in managing distributed, sensitive data is to measure the extent to which a distribution changes. Understanding this drift can effectively support a variety of federated learning and analytics tasks. However, in many practical settings sharing such information can be undesirable (e.g., for privacy concerns) or infeasible (e.g., for high communication costs). In this work, we describe novel algorithmic approaches for estimating the KL divergence of data across federated models of computation, under differential privacy. We analyze their theoretical properties and present an empirical"},"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":"2411.16478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T15:20:40Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"c35979d1faaedd38af6891a3731aec87084fdf7305b5435576bccaf9c85d237e","abstract_canon_sha256":"e8f9ddb68390af3427e3c0f11c0846321c076a11e303778cd854b7bc723a30bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:46.828361Z","signature_b64":"RnOx69r/cD4CBMIGgV+s1ceWkmJaCch6oHeageaexLQ+gmi/AnmSZ0l7hUb4iJbNQ1ELY4a25hTRq6I3oszaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afd10ea626c4ef0bbd8870645eab719c8d500c928ca41f4fb7f9e0ee489b4621","last_reissued_at":"2026-07-05T09:41:46.827849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:46.827849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed, communication-efficient, and differentially private estimation of KL divergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Carsten Maple, Graham Cormode, Mary Scott, Sayan Biswas","submitted_at":"2024-11-25T15:20:40Z","abstract_excerpt":"A key task in managing distributed, sensitive data is to measure the extent to which a distribution changes. Understanding this drift can effectively support a variety of federated learning and analytics tasks. However, in many practical settings sharing such information can be undesirable (e.g., for privacy concerns) or infeasible (e.g., for high communication costs). In this work, we describe novel algorithmic approaches for estimating the KL divergence of data across federated models of computation, under differential privacy. We analyze their theoretical properties and present an empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16478","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/2411.16478/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":"2411.16478","created_at":"2026-07-05T09:41:46.827907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16478v2","created_at":"2026-07-05T09:41:46.827907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16478","created_at":"2026-07-05T09:41:46.827907+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7IQ5JRGYTXQ","created_at":"2026-07-05T09:41:46.827907+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7IQ5JRGYTXQXPMI","created_at":"2026-07-05T09:41:46.827907+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7IQ5JRG","created_at":"2026-07-05T09:41:46.827907+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/V7IQ5JRGYTXQXPMIOBSF5K3RTS","json":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS.json","graph_json":"https://pith.science/api/pith-number/V7IQ5JRGYTXQXPMIOBSF5K3RTS/graph.json","events_json":"https://pith.science/api/pith-number/V7IQ5JRGYTXQXPMIOBSF5K3RTS/events.json","paper":"https://pith.science/paper/V7IQ5JRG"},"agent_actions":{"view_html":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS","download_json":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS.json","view_paper":"https://pith.science/paper/V7IQ5JRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16478&json=true","fetch_graph":"https://pith.science/api/pith-number/V7IQ5JRGYTXQXPMIOBSF5K3RTS/graph.json","fetch_events":"https://pith.science/api/pith-number/V7IQ5JRGYTXQXPMIOBSF5K3RTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS/action/storage_attestation","attest_author":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS/action/author_attestation","sign_citation":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS/action/citation_signature","submit_replication":"https://pith.science/pith/V7IQ5JRGYTXQXPMIOBSF5K3RTS/action/replication_record"}},"created_at":"2026-07-05T09:41:46.827907+00:00","updated_at":"2026-07-05T09:41:46.827907+00:00"}