{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GJBFDTO7MQ7RU27YFYDFAFO7YB","short_pith_number":"pith:GJBFDTO7","schema_version":"1.0","canonical_sha256":"324251cddf643f1a6bf82e065015dfc056ee7ad1ab7bd7db33820575a8ca758d","source":{"kind":"arxiv","id":"2012.13891","version":3},"attestation_state":"computed","paper":{"title":"Federated Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chen Wang, Gaoyang Liu, Jiangchuan Liu, Xiaoqiang Ma, Yang Yang","submitted_at":"2020-12-27T08:54:37Z","abstract_excerpt":"Federated learning (FL) has recently emerged as a promising distributed machine learning (ML) paradigm. Practical needs of the \"right to be forgotten\" and countering data poisoning attacks call for efficient techniques that can remove, or unlearn, specific training data from the trained FL model. Existing unlearning techniques in the context of ML, however, are no longer in effect for FL, mainly due to the inherent distinction in the way how FL and ML learn from data. Therefore, how to enable efficient data removal from FL models remains largely under-explored. In this paper, we take the first"},"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":"2012.13891","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-27T08:54:37Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"152d9861e9f2eb2bdae5d599aa4751b1e98ddcb1f9e83afeed8a9299a1bac5c3","abstract_canon_sha256":"b14cd717b56942130d9b47749bd4133f7b8344072c553fa21f70ae55f6468c5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:57.468869Z","signature_b64":"2DhTZUzaaq7NT9oX/cADWa5yotlyg+IV6+Qf+rEM+AGJeikGC9BMsPN9gv5mNiK3pm7F/AbONl04cEW5C7K4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"324251cddf643f1a6bf82e065015dfc056ee7ad1ab7bd7db33820575a8ca758d","last_reissued_at":"2026-07-05T02:37:57.468416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:57.468416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chen Wang, Gaoyang Liu, Jiangchuan Liu, Xiaoqiang Ma, Yang Yang","submitted_at":"2020-12-27T08:54:37Z","abstract_excerpt":"Federated learning (FL) has recently emerged as a promising distributed machine learning (ML) paradigm. Practical needs of the \"right to be forgotten\" and countering data poisoning attacks call for efficient techniques that can remove, or unlearn, specific training data from the trained FL model. Existing unlearning techniques in the context of ML, however, are no longer in effect for FL, mainly due to the inherent distinction in the way how FL and ML learn from data. Therefore, how to enable efficient data removal from FL models remains largely under-explored. In this paper, we take the first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13891","kind":"arxiv","version":3},"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/2012.13891/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":"2012.13891","created_at":"2026-07-05T02:37:57.468473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13891v3","created_at":"2026-07-05T02:37:57.468473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13891","created_at":"2026-07-05T02:37:57.468473+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJBFDTO7MQ7R","created_at":"2026-07-05T02:37:57.468473+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJBFDTO7MQ7RU27Y","created_at":"2026-07-05T02:37:57.468473+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJBFDTO7","created_at":"2026-07-05T02:37:57.468473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07141","citing_title":"REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2310.16789","citing_title":"Detecting Pretraining Data from Large Language Models","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23798","citing_title":"MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB","json":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB.json","graph_json":"https://pith.science/api/pith-number/GJBFDTO7MQ7RU27YFYDFAFO7YB/graph.json","events_json":"https://pith.science/api/pith-number/GJBFDTO7MQ7RU27YFYDFAFO7YB/events.json","paper":"https://pith.science/paper/GJBFDTO7"},"agent_actions":{"view_html":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB","download_json":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB.json","view_paper":"https://pith.science/paper/GJBFDTO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13891&json=true","fetch_graph":"https://pith.science/api/pith-number/GJBFDTO7MQ7RU27YFYDFAFO7YB/graph.json","fetch_events":"https://pith.science/api/pith-number/GJBFDTO7MQ7RU27YFYDFAFO7YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB/action/storage_attestation","attest_author":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB/action/author_attestation","sign_citation":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB/action/citation_signature","submit_replication":"https://pith.science/pith/GJBFDTO7MQ7RU27YFYDFAFO7YB/action/replication_record"}},"created_at":"2026-07-05T02:37:57.468473+00:00","updated_at":"2026-07-05T02:37:57.468473+00:00"}