{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RIIM3JPX4BBFA6G4MSLDIEM5MR","short_pith_number":"pith:RIIM3JPX","schema_version":"1.0","canonical_sha256":"8a10cda5f7e0425078dc649634119d646a06d57aabb5005879eb2e3e7172a61b","source":{"kind":"arxiv","id":"2012.11035","version":2},"attestation_state":"computed","paper":{"title":"Contraction of $E_\\gamma$-Divergence and Its Applications to Privacy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Flavio P. Calmon, Mario Diaz, Shahab Asoodeh","submitted_at":"2020-12-20T22:02:15Z","abstract_excerpt":"We investigate the contraction coefficients derived from strong data processing inequalities for the $E_\\gamma$-divergence. By generalizing the celebrated Dobrushin's coefficient from total variation distance to $E_\\gamma$-divergence, we derive a closed-form expression for the contraction of $E_\\gamma$-divergence. This result has fundamental consequences in two privacy settings. First, it implies that local differential privacy can be equivalently expressed in terms of the contraction of $E_\\gamma$-divergence. This equivalent formula can be used to precisely quantify the impact of local privac"},"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":"2012.11035","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2020-12-20T22:02:15Z","cross_cats_sorted":["cs.CR","cs.LG","math.IT","stat.ML"],"title_canon_sha256":"1ecba15ebefd43e5a8f9774319c8b7c28addf39481c6ba1f1927c2bfcf206c83","abstract_canon_sha256":"f1be111e2107d2b7b7c4fa6a368171f2d321e9e14d77d67d7a4689038eed1033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:29.541703Z","signature_b64":"HLxMv66eGbJRx86U3WoXvmQXJUN2Do1qmFjvZlMQLv71zOwGAnrTwPcR4K6nt9c8+F56Yjlyzz8FCiw/NDWZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a10cda5f7e0425078dc649634119d646a06d57aabb5005879eb2e3e7172a61b","last_reissued_at":"2026-07-05T05:40:29.541361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:29.541361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contraction of $E_\\gamma$-Divergence and Its Applications to Privacy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Flavio P. Calmon, Mario Diaz, Shahab Asoodeh","submitted_at":"2020-12-20T22:02:15Z","abstract_excerpt":"We investigate the contraction coefficients derived from strong data processing inequalities for the $E_\\gamma$-divergence. By generalizing the celebrated Dobrushin's coefficient from total variation distance to $E_\\gamma$-divergence, we derive a closed-form expression for the contraction of $E_\\gamma$-divergence. This result has fundamental consequences in two privacy settings. First, it implies that local differential privacy can be equivalently expressed in terms of the contraction of $E_\\gamma$-divergence. This equivalent formula can be used to precisely quantify the impact of local privac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11035","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/2012.11035/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":"2012.11035","created_at":"2026-07-05T05:40:29.541417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11035v2","created_at":"2026-07-05T05:40:29.541417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11035","created_at":"2026-07-05T05:40:29.541417+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIIM3JPX4BBF","created_at":"2026-07-05T05:40:29.541417+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIIM3JPX4BBFA6G4","created_at":"2026-07-05T05:40:29.541417+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIIM3JPX","created_at":"2026-07-05T05:40:29.541417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.07999","citing_title":"Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08964","citing_title":"Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR","json":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR.json","graph_json":"https://pith.science/api/pith-number/RIIM3JPX4BBFA6G4MSLDIEM5MR/graph.json","events_json":"https://pith.science/api/pith-number/RIIM3JPX4BBFA6G4MSLDIEM5MR/events.json","paper":"https://pith.science/paper/RIIM3JPX"},"agent_actions":{"view_html":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR","download_json":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR.json","view_paper":"https://pith.science/paper/RIIM3JPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11035&json=true","fetch_graph":"https://pith.science/api/pith-number/RIIM3JPX4BBFA6G4MSLDIEM5MR/graph.json","fetch_events":"https://pith.science/api/pith-number/RIIM3JPX4BBFA6G4MSLDIEM5MR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR/action/storage_attestation","attest_author":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR/action/author_attestation","sign_citation":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR/action/citation_signature","submit_replication":"https://pith.science/pith/RIIM3JPX4BBFA6G4MSLDIEM5MR/action/replication_record"}},"created_at":"2026-07-05T05:40:29.541417+00:00","updated_at":"2026-07-05T05:40:29.541417+00:00"}