{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6ZAEX7YCAUTRILFBUO3SA5IHE6","short_pith_number":"pith:6ZAEX7YC","schema_version":"1.0","canonical_sha256":"f6404bff020527142ca1a3b720750727a910944bb106337d1cda3e70f53f741e","source":{"kind":"arxiv","id":"2303.17591","version":1},"attestation_state":"computed","paper":{"title":"Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Zhang, Humphrey Shi, Kai Wang, Xingqian Xu, Zhangyang Wang","submitted_at":"2023-03-30T17:58:11Z","abstract_excerpt":"The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy, copyright, and safety, as numerous unauthorized personal IDs, content, artistic creations, and potentially harmful materials have been learned by these models and later utilized to generate and distribute uncontrolled content. To address this challenge, we propose \\textbf{Forget-Me-Not}, an efficient and low-cost solution designed to safely remove specified I"},"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":"2303.17591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:58:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a26b41dfbd59a9131589a807d7963191d64a414b6766fed7b4b4b58b2f9900f8","abstract_canon_sha256":"17bbe86ad67bf6c2f6897a965e2ca2c1c51623946c56084a5dddf00bf92599ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:35.888423Z","signature_b64":"U30p9y2kGkLeYI6Z6PyosOfbSDA08TTbDlQsahBqijmY/X53EIqbkv12CJc/7GqxrIz1CDBcGyYw86sr+GJfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6404bff020527142ca1a3b720750727a910944bb106337d1cda3e70f53f741e","last_reissued_at":"2026-07-05T05:56:35.887995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:35.887995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Zhang, Humphrey Shi, Kai Wang, Xingqian Xu, Zhangyang Wang","submitted_at":"2023-03-30T17:58:11Z","abstract_excerpt":"The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy, copyright, and safety, as numerous unauthorized personal IDs, content, artistic creations, and potentially harmful materials have been learned by these models and later utilized to generate and distribute uncontrolled content. To address this challenge, we propose \\textbf{Forget-Me-Not}, an efficient and low-cost solution designed to safely remove specified I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17591","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/2303.17591/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":"2303.17591","created_at":"2026-07-05T05:56:35.888053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17591v1","created_at":"2026-07-05T05:56:35.888053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17591","created_at":"2026-07-05T05:56:35.888053+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZAEX7YCAUTR","created_at":"2026-07-05T05:56:35.888053+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZAEX7YCAUTRILFB","created_at":"2026-07-05T05:56:35.888053+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZAEX7YC","created_at":"2026-07-05T05:56:35.888053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02453","citing_title":"Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16481","citing_title":"Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6","json":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6.json","graph_json":"https://pith.science/api/pith-number/6ZAEX7YCAUTRILFBUO3SA5IHE6/graph.json","events_json":"https://pith.science/api/pith-number/6ZAEX7YCAUTRILFBUO3SA5IHE6/events.json","paper":"https://pith.science/paper/6ZAEX7YC"},"agent_actions":{"view_html":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6","download_json":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6.json","view_paper":"https://pith.science/paper/6ZAEX7YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17591&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZAEX7YCAUTRILFBUO3SA5IHE6/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZAEX7YCAUTRILFBUO3SA5IHE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6/action/storage_attestation","attest_author":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6/action/author_attestation","sign_citation":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6/action/citation_signature","submit_replication":"https://pith.science/pith/6ZAEX7YCAUTRILFBUO3SA5IHE6/action/replication_record"}},"created_at":"2026-07-05T05:56:35.888053+00:00","updated_at":"2026-07-05T05:56:35.888053+00:00"}