{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IQBI2R7PA3S4F35UNMILDX7TU5","short_pith_number":"pith:IQBI2R7P","schema_version":"1.0","canonical_sha256":"44028d47ef06e5c2efb46b10b1dff3a763c7b5248ce1b0c3da03e931eaf70475","source":{"kind":"arxiv","id":"1812.00984","version":2},"attestation_state":"computed","paper":{"title":"Protection Against Reconstruction and Its Applications in Private Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Abhishek Bhowmick, Gaurav Kapoor, John Duchi, Julien Freudiger, Ryan Rogers","submitted_at":"2018-12-03T18:59:16Z","abstract_excerpt":"In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in decentralized data are increasing challenges of maintaining privacy while allowing enough information to fit accurate, useful statistical models. This motivates local notions of privacy---most significantly, local differential privacy, which provides strong protections against sensitive data disclosures---where data is obfuscated before a statistician or learner can eve"},"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":"1812.00984","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-03T18:59:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e8f99a528f64b70e7667c0f657016cf36ba7a4a1d41b65108be9c5d9d5ae7ea","abstract_canon_sha256":"838aee80a224dd3abe2ba5dbb6d7d3e5f1bdeb2aa541c0c7096de546455f6bfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:29.808640Z","signature_b64":"yfrSkrqYJW/hiEBeg3RgD1MIIOpF4+WhmBBMje1/0OzK2r7t5QQH7hVET9ON6CcLEE+YUeKx/KRFtYvm9GbaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44028d47ef06e5c2efb46b10b1dff3a763c7b5248ce1b0c3da03e931eaf70475","last_reissued_at":"2026-05-17T23:44:29.808097Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:29.808097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protection Against Reconstruction and Its Applications in Private Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Abhishek Bhowmick, Gaurav Kapoor, John Duchi, Julien Freudiger, Ryan Rogers","submitted_at":"2018-12-03T18:59:16Z","abstract_excerpt":"In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in decentralized data are increasing challenges of maintaining privacy while allowing enough information to fit accurate, useful statistical models. This motivates local notions of privacy---most significantly, local differential privacy, which provides strong protections against sensitive data disclosures---where data is obfuscated before a statistician or learner can eve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00984","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":""},"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":"1812.00984","created_at":"2026-05-17T23:44:29.808194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00984v2","created_at":"2026-05-17T23:44:29.808194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00984","created_at":"2026-05-17T23:44:29.808194+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQBI2R7PA3S4","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQBI2R7PA3S4F35U","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQBI2R7P","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2404.02696","citing_title":"Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21860","citing_title":"Robust Statistical Estimators with Bounded Empirical Sensitivity","ref_index":181,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28032","citing_title":"Shuffling-Aware Optimization for Private Vector Mean Estimation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23426","citing_title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5","json":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5.json","graph_json":"https://pith.science/api/pith-number/IQBI2R7PA3S4F35UNMILDX7TU5/graph.json","events_json":"https://pith.science/api/pith-number/IQBI2R7PA3S4F35UNMILDX7TU5/events.json","paper":"https://pith.science/paper/IQBI2R7P"},"agent_actions":{"view_html":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5","download_json":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5.json","view_paper":"https://pith.science/paper/IQBI2R7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00984&json=true","fetch_graph":"https://pith.science/api/pith-number/IQBI2R7PA3S4F35UNMILDX7TU5/graph.json","fetch_events":"https://pith.science/api/pith-number/IQBI2R7PA3S4F35UNMILDX7TU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5/action/storage_attestation","attest_author":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5/action/author_attestation","sign_citation":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5/action/citation_signature","submit_replication":"https://pith.science/pith/IQBI2R7PA3S4F35UNMILDX7TU5/action/replication_record"}},"created_at":"2026-05-17T23:44:29.808194+00:00","updated_at":"2026-05-17T23:44:29.808194+00:00"}