{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AHRCLHQPPMFXGAYWHC75V2PYLA","short_pith_number":"pith:AHRCLHQP","schema_version":"1.0","canonical_sha256":"01e2259e0f7b0b73031638bfdae9f858064b3933d504f27089aa6ac44a910ea7","source":{"kind":"arxiv","id":"2406.18566","version":1},"attestation_state":"computed","paper":{"title":"Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Li, Ondrej Bohdal, Ruchika Chavhan, Timothy Hospedales, Yongshuo Zong","submitted_at":"2024-06-01T15:47:13Z","abstract_excerpt":"Large-scale text-to-image diffusion models excel in generating high-quality images from textual inputs, yet concerns arise as research indicates their tendency to memorize and replicate training data, raising We also addressed the issue of memorization in diffusion models, where models tend to replicate exact training samples raising copyright infringement and privacy issues. Efforts within the text-to-image community to address memorization explore causes such as data duplication, replicated captions, or trigger tokens, proposing per-prompt inference-time or training-time mitigation strategie"},"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":"2406.18566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T15:47:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c0195edabf54b7cb2fb407d99d0dad3704af6b7f84fa6c24fa53fb8d6d8a6baa","abstract_canon_sha256":"f71eb61f78b5e4ff9938d7bfd0bfd0ce9ab5c1493af1aade3c146e69c60515f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:22.511948Z","signature_b64":"OcWb0vy+/w3KrAwHMGBOBNvb3dHN7ANYhIJVfXuT4wbX+P7bOt7HkIlRId8z/zYgv/T950lincWy9XjsGEZFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e2259e0f7b0b73031638bfdae9f858064b3933d504f27089aa6ac44a910ea7","last_reissued_at":"2026-07-05T08:37:22.511481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:22.511481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Li, Ondrej Bohdal, Ruchika Chavhan, Timothy Hospedales, Yongshuo Zong","submitted_at":"2024-06-01T15:47:13Z","abstract_excerpt":"Large-scale text-to-image diffusion models excel in generating high-quality images from textual inputs, yet concerns arise as research indicates their tendency to memorize and replicate training data, raising We also addressed the issue of memorization in diffusion models, where models tend to replicate exact training samples raising copyright infringement and privacy issues. Efforts within the text-to-image community to address memorization explore causes such as data duplication, replicated captions, or trigger tokens, proposing per-prompt inference-time or training-time mitigation strategie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18566","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/2406.18566/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":"2406.18566","created_at":"2026-07-05T08:37:22.511539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18566v1","created_at":"2026-07-05T08:37:22.511539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18566","created_at":"2026-07-05T08:37:22.511539+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHRCLHQPPMFX","created_at":"2026-07-05T08:37:22.511539+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHRCLHQPPMFXGAYW","created_at":"2026-07-05T08:37:22.511539+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHRCLHQP","created_at":"2026-07-05T08:37:22.511539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22050","citing_title":"Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22050","citing_title":"Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22050","citing_title":"Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10439","citing_title":"Filtering Memorization from Parameter-Space in Diffusion Models","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA","json":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA.json","graph_json":"https://pith.science/api/pith-number/AHRCLHQPPMFXGAYWHC75V2PYLA/graph.json","events_json":"https://pith.science/api/pith-number/AHRCLHQPPMFXGAYWHC75V2PYLA/events.json","paper":"https://pith.science/paper/AHRCLHQP"},"agent_actions":{"view_html":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA","download_json":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA.json","view_paper":"https://pith.science/paper/AHRCLHQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18566&json=true","fetch_graph":"https://pith.science/api/pith-number/AHRCLHQPPMFXGAYWHC75V2PYLA/graph.json","fetch_events":"https://pith.science/api/pith-number/AHRCLHQPPMFXGAYWHC75V2PYLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA/action/storage_attestation","attest_author":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA/action/author_attestation","sign_citation":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA/action/citation_signature","submit_replication":"https://pith.science/pith/AHRCLHQPPMFXGAYWHC75V2PYLA/action/replication_record"}},"created_at":"2026-07-05T08:37:22.511539+00:00","updated_at":"2026-07-05T08:37:22.511539+00:00"}