{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZAE2D7M22GL2XOQKYZ3U7HX6PG","short_pith_number":"pith:ZAE2D7M2","schema_version":"1.0","canonical_sha256":"c809a1fd9ad197abba0ac6774f9efe799469390a3c107a0a911c668cece20e36","source":{"kind":"arxiv","id":"2006.07490","version":1},"attestation_state":"computed","paper":{"title":"Understanding Unintended Memorization in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fran\\c{c}oise Beaufays, Om Thakkar, Rajiv Mathews, Swaroop Ramaswamy","submitted_at":"2020-06-12T22:10:16Z","abstract_excerpt":"Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are often trained on sensitive data, to ensure the privacy of the training data it is critical to identify and mitigate such unintended memorization. Federated Learning (FL) has emerged as a novel framework for large-scale distributed learning tasks. However, it differs in many aspects from the well-studied central learning setting where all the data is stored at the central server. In this paper, we initiate a formal stu"},"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":"2006.07490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T22:10:16Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"4a1a035f1602e60be1fa88e2e7a829f929a9705f1d0379084716a7b876c0bc14","abstract_canon_sha256":"2c2da7786a209f5a5c2c886dfb23a0a37d475c4b86d0dc1fdfde5ba69f52c273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:00.581934Z","signature_b64":"kQBBS94qPWjO5QQNSiK6mSlqGKbx1M9TN0c1AThdZvS/K6zfs16CkjpR1d68Ma8wKSpaPFXnNJ7ytW26gyFfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c809a1fd9ad197abba0ac6774f9efe799469390a3c107a0a911c668cece20e36","last_reissued_at":"2026-07-05T01:10:00.581422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:00.581422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Unintended Memorization in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fran\\c{c}oise Beaufays, Om Thakkar, Rajiv Mathews, Swaroop Ramaswamy","submitted_at":"2020-06-12T22:10:16Z","abstract_excerpt":"Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are often trained on sensitive data, to ensure the privacy of the training data it is critical to identify and mitigate such unintended memorization. Federated Learning (FL) has emerged as a novel framework for large-scale distributed learning tasks. However, it differs in many aspects from the well-studied central learning setting where all the data is stored at the central server. In this paper, we initiate a formal stu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07490","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/2006.07490/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":"2006.07490","created_at":"2026-07-05T01:10:00.581487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07490v1","created_at":"2026-07-05T01:10:00.581487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07490","created_at":"2026-07-05T01:10:00.581487+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAE2D7M22GL2","created_at":"2026-07-05T01:10:00.581487+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAE2D7M22GL2XOQK","created_at":"2026-07-05T01:10:00.581487+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAE2D7M2","created_at":"2026-07-05T01:10:00.581487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":191,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG","json":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG.json","graph_json":"https://pith.science/api/pith-number/ZAE2D7M22GL2XOQKYZ3U7HX6PG/graph.json","events_json":"https://pith.science/api/pith-number/ZAE2D7M22GL2XOQKYZ3U7HX6PG/events.json","paper":"https://pith.science/paper/ZAE2D7M2"},"agent_actions":{"view_html":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG","download_json":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG.json","view_paper":"https://pith.science/paper/ZAE2D7M2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07490&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAE2D7M22GL2XOQKYZ3U7HX6PG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAE2D7M22GL2XOQKYZ3U7HX6PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG/action/storage_attestation","attest_author":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG/action/author_attestation","sign_citation":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG/action/citation_signature","submit_replication":"https://pith.science/pith/ZAE2D7M22GL2XOQKYZ3U7HX6PG/action/replication_record"}},"created_at":"2026-07-05T01:10:00.581487+00:00","updated_at":"2026-07-05T01:10:00.581487+00:00"}