{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QSH7WNR6VQJO74CYH6L3ZLETWR","short_pith_number":"pith:QSH7WNR6","schema_version":"1.0","canonical_sha256":"848ffb363eac12eff0583f97bcac93b465e469f5badbdbe71f3e90c63bae8d14","source":{"kind":"arxiv","id":"2402.11846","version":4},"attestation_state":"computed","paper":{"title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Fan, Gaowen Liu, Gaoyuan Zhang, Jiancheng Liu, Jinghan Jia, Ramana Rao Kompella, Sijia Liu, Xiaoming Liu, Yihua Zhang, Yimeng Zhang, Yuguang Yao","submitted_at":"2024-02-19T05:25:53Z","abstract_excerpt":"The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose Unlearn"},"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":"2402.11846","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-19T05:25:53Z","cross_cats_sorted":[],"title_canon_sha256":"e864147bc436a1fc916195e3a6a49c3ed4fde0521d2d97620ec4e390f4a762c8","abstract_canon_sha256":"9f607cfab14f703e9c34019064c75537fdf590ec4d2b1be3bddec4bfacfc75c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:10.730106Z","signature_b64":"Jr1wCuRXftoC8ocS5gstS0TqrnhvIp7o+HydxOX6Pk+HHaJEl7WhIYV3mXv7ZCk80y1qopnWsIOy6b6M6pamAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"848ffb363eac12eff0583f97bcac93b465e469f5badbdbe71f3e90c63bae8d14","last_reissued_at":"2026-07-05T09:28:10.729561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:10.729561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Fan, Gaowen Liu, Gaoyuan Zhang, Jiancheng Liu, Jinghan Jia, Ramana Rao Kompella, Sijia Liu, Xiaoming Liu, Yihua Zhang, Yimeng Zhang, Yuguang Yao","submitted_at":"2024-02-19T05:25:53Z","abstract_excerpt":"The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose Unlearn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11846","kind":"arxiv","version":4},"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/2402.11846/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":"2402.11846","created_at":"2026-07-05T09:28:10.729619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11846v4","created_at":"2026-07-05T09:28:10.729619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11846","created_at":"2026-07-05T09:28:10.729619+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSH7WNR6VQJO","created_at":"2026-07-05T09:28:10.729619+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSH7WNR6VQJO74CY","created_at":"2026-07-05T09:28:10.729619+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSH7WNR6","created_at":"2026-07-05T09:28:10.729619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07907","citing_title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02453","citing_title":"Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2405.07406","citing_title":"Machine Unlearning: A Comprehensive Survey","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08218","citing_title":"Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":129,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR","json":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR.json","graph_json":"https://pith.science/api/pith-number/QSH7WNR6VQJO74CYH6L3ZLETWR/graph.json","events_json":"https://pith.science/api/pith-number/QSH7WNR6VQJO74CYH6L3ZLETWR/events.json","paper":"https://pith.science/paper/QSH7WNR6"},"agent_actions":{"view_html":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR","download_json":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR.json","view_paper":"https://pith.science/paper/QSH7WNR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11846&json=true","fetch_graph":"https://pith.science/api/pith-number/QSH7WNR6VQJO74CYH6L3ZLETWR/graph.json","fetch_events":"https://pith.science/api/pith-number/QSH7WNR6VQJO74CYH6L3ZLETWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR/action/storage_attestation","attest_author":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR/action/author_attestation","sign_citation":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR/action/citation_signature","submit_replication":"https://pith.science/pith/QSH7WNR6VQJO74CYH6L3ZLETWR/action/replication_record"}},"created_at":"2026-07-05T09:28:10.729619+00:00","updated_at":"2026-07-05T09:28:10.729619+00:00"}