{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2HHTCAQPJDZYPOZF24TYHVJ46R","short_pith_number":"pith:2HHTCAQP","schema_version":"1.0","canonical_sha256":"d1cf31020f48f387bb25d72783d53cf44ebdb1fcdff88f75c35fe9fe2a1cbe69","source":{"kind":"arxiv","id":"2403.15779","version":1},"attestation_state":"computed","paper":{"title":"The Frontier of Data Erasure: Machine Unlearning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dusit Niyato, Kanchana Thilakarathna, Ming Ding, Nan Sun, Tianqing Zhu, Youyang Qu","submitted_at":"2024-03-23T09:26:15Z","abstract_excerpt":"Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information from their vast datasets. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns, offering techniques for LLMs to selectively discard certain data. This paper reviews the latest in machine unlearning for LLMs, introducing methods for the targeted forgetting of information to address privacy, ethical, and legal challenges without"},"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":"2403.15779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-23T09:26:15Z","cross_cats_sorted":[],"title_canon_sha256":"ef3499558b03504fe6ca31385db2a57a669acf258c3c9d46cdbfa5d41ee92598","abstract_canon_sha256":"ed043f9dfcb1e2b22c6923cca3b5480ac6e4043939f23c16d9eb01824e67f07e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:06.221610Z","signature_b64":"/gF8eWFBReo+Vn9ISh0+e/aCa138xQ66xSB10q3lhemUtUE+KyM18jehxuuA6HmMrJdknWdpVDk8apQTITDcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1cf31020f48f387bb25d72783d53cf44ebdb1fcdff88f75c35fe9fe2a1cbe69","last_reissued_at":"2026-07-05T08:00:06.221117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:06.221117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Frontier of Data Erasure: Machine Unlearning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dusit Niyato, Kanchana Thilakarathna, Ming Ding, Nan Sun, Tianqing Zhu, Youyang Qu","submitted_at":"2024-03-23T09:26:15Z","abstract_excerpt":"Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information from their vast datasets. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns, offering techniques for LLMs to selectively discard certain data. This paper reviews the latest in machine unlearning for LLMs, introducing methods for the targeted forgetting of information to address privacy, ethical, and legal challenges without"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15779","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/2403.15779/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":"2403.15779","created_at":"2026-07-05T08:00:06.221175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15779v1","created_at":"2026-07-05T08:00:06.221175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15779","created_at":"2026-07-05T08:00:06.221175+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HHTCAQPJDZY","created_at":"2026-07-05T08:00:06.221175+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HHTCAQPJDZYPOZF","created_at":"2026-07-05T08:00:06.221175+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HHTCAQP","created_at":"2026-07-05T08:00:06.221175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.15115","citing_title":"Towards Reliable Forgetting: A Survey on Machine Unlearning Verification","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20941","citing_title":"Revisiting the Past: Data Unlearning with Model State History","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R","json":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R.json","graph_json":"https://pith.science/api/pith-number/2HHTCAQPJDZYPOZF24TYHVJ46R/graph.json","events_json":"https://pith.science/api/pith-number/2HHTCAQPJDZYPOZF24TYHVJ46R/events.json","paper":"https://pith.science/paper/2HHTCAQP"},"agent_actions":{"view_html":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R","download_json":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R.json","view_paper":"https://pith.science/paper/2HHTCAQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15779&json=true","fetch_graph":"https://pith.science/api/pith-number/2HHTCAQPJDZYPOZF24TYHVJ46R/graph.json","fetch_events":"https://pith.science/api/pith-number/2HHTCAQPJDZYPOZF24TYHVJ46R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R/action/storage_attestation","attest_author":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R/action/author_attestation","sign_citation":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R/action/citation_signature","submit_replication":"https://pith.science/pith/2HHTCAQPJDZYPOZF24TYHVJ46R/action/replication_record"}},"created_at":"2026-07-05T08:00:06.221175+00:00","updated_at":"2026-07-05T08:00:06.221175+00:00"}