{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:24FLZXICV4NJ7RFW6B3QB4BNIH","short_pith_number":"pith:24FLZXIC","schema_version":"1.0","canonical_sha256":"d70abcdd02af1a9fc4b6f07700f02d41e6ac0045a434783c222b588c5ac9b9f5","source":{"kind":"arxiv","id":"2203.03594","version":1},"attestation_state":"computed","paper":{"title":"Continual and Sliding Window Release for Private Empirical Risk Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhirup Ghosh, Benedek Rozemberczki, Lauren Watson, Rik Sarkar","submitted_at":"2022-03-07T18:44:16Z","abstract_excerpt":"It is difficult to continually update private machine learning models with new data while maintaining privacy. Data incur increasing privacy loss -- as measured by differential privacy -- when they are used in repeated computations. In this paper, we describe regularized empirical risk minimization algorithms that continually release models for a recent window of data. One version of the algorithm uses the entire data history to improve the model for the recent window. The second version uses a sliding window of constant size to improve the model, ensuring more relevant models in case of evolv"},"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":"2203.03594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T18:44:16Z","cross_cats_sorted":[],"title_canon_sha256":"397ba158cd114d4c55f021f7d59c9747467fe2ec033f88f62898bd40e12f05ec","abstract_canon_sha256":"1965e88b52c113e81974b905e7c6417154a1d1b96d4f8dc913012a125ce78bd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:36.185122Z","signature_b64":"6jo58wxU8jSsQBKK2jtugp7GrJ2eSW/oqpAROknywlqRCZgx4zLDmZx/f9x6hjgzHwbpULI9iUlobGiJcR1aCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d70abcdd02af1a9fc4b6f07700f02d41e6ac0045a434783c222b588c5ac9b9f5","last_reissued_at":"2026-07-05T04:02:36.184630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:36.184630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual and Sliding Window Release for Private Empirical Risk Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhirup Ghosh, Benedek Rozemberczki, Lauren Watson, Rik Sarkar","submitted_at":"2022-03-07T18:44:16Z","abstract_excerpt":"It is difficult to continually update private machine learning models with new data while maintaining privacy. Data incur increasing privacy loss -- as measured by differential privacy -- when they are used in repeated computations. In this paper, we describe regularized empirical risk minimization algorithms that continually release models for a recent window of data. One version of the algorithm uses the entire data history to improve the model for the recent window. The second version uses a sliding window of constant size to improve the model, ensuring more relevant models in case of evolv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03594","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/2203.03594/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":"2203.03594","created_at":"2026-07-05T04:02:36.184682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03594v1","created_at":"2026-07-05T04:02:36.184682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03594","created_at":"2026-07-05T04:02:36.184682+00:00"},{"alias_kind":"pith_short_12","alias_value":"24FLZXICV4NJ","created_at":"2026-07-05T04:02:36.184682+00:00"},{"alias_kind":"pith_short_16","alias_value":"24FLZXICV4NJ7RFW","created_at":"2026-07-05T04:02:36.184682+00:00"},{"alias_kind":"pith_short_8","alias_value":"24FLZXIC","created_at":"2026-07-05T04:02:36.184682+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/24FLZXICV4NJ7RFW6B3QB4BNIH","json":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH.json","graph_json":"https://pith.science/api/pith-number/24FLZXICV4NJ7RFW6B3QB4BNIH/graph.json","events_json":"https://pith.science/api/pith-number/24FLZXICV4NJ7RFW6B3QB4BNIH/events.json","paper":"https://pith.science/paper/24FLZXIC"},"agent_actions":{"view_html":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH","download_json":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH.json","view_paper":"https://pith.science/paper/24FLZXIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03594&json=true","fetch_graph":"https://pith.science/api/pith-number/24FLZXICV4NJ7RFW6B3QB4BNIH/graph.json","fetch_events":"https://pith.science/api/pith-number/24FLZXICV4NJ7RFW6B3QB4BNIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH/action/storage_attestation","attest_author":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH/action/author_attestation","sign_citation":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH/action/citation_signature","submit_replication":"https://pith.science/pith/24FLZXICV4NJ7RFW6B3QB4BNIH/action/replication_record"}},"created_at":"2026-07-05T04:02:36.184682+00:00","updated_at":"2026-07-05T04:02:36.184682+00:00"}