{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NUESBE3GOZYKYTG7OFKBEAVPTI","short_pith_number":"pith:NUESBE3G","schema_version":"1.0","canonical_sha256":"6d092093667670ac4cdf71541202af9a27e5b5f82c35148df4f54f8b05934d90","source":{"kind":"arxiv","id":"2510.17917","version":2},"attestation_state":"computed","paper":{"title":"Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jinseong Park, Mijung Park","submitted_at":"2025-10-20T02:00:12Z","abstract_excerpt":"Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies primarily on loss maximization over forget samples, which often leads to quality degradation or incomplete forgetting. Existing methods perform unlearning uniformly across diffusion stages, ignoring diffusion dynamics from noise to data. Our systematic study of diffusion phases shows that forgetting in diffusion models is uneven across time and frequency, with theoretical justification of distributive distortion and forgetting-utility trade-off. By sele"},"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":"2510.17917","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-20T02:00:12Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"570e6bf6b4046c9bf5ccd2a12a134fd83ad44dbe75d0efb50a8d7ccb646b0ac1","abstract_canon_sha256":"de166ade91cd5c418f5dc7a0472e329a57114bd45353a00893dd5878a61156f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:42.332754Z","signature_b64":"cqxnWEXE+pJplHvQTY+Qs/KTXN5N+ldHzV4I3gvWJAvJabErHS0Py7EJkVl2SrUjF4Yf0QzcDEKdk53myBkuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d092093667670ac4cdf71541202af9a27e5b5f82c35148df4f54f8b05934d90","last_reissued_at":"2026-07-01T01:17:42.332223Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:42.332223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jinseong Park, Mijung Park","submitted_at":"2025-10-20T02:00:12Z","abstract_excerpt":"Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies primarily on loss maximization over forget samples, which often leads to quality degradation or incomplete forgetting. Existing methods perform unlearning uniformly across diffusion stages, ignoring diffusion dynamics from noise to data. Our systematic study of diffusion phases shows that forgetting in diffusion models is uneven across time and frequency, with theoretical justification of distributive distortion and forgetting-utility trade-off. By sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.17917","kind":"arxiv","version":2},"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/2510.17917/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":"2510.17917","created_at":"2026-07-01T01:17:42.332293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.17917v2","created_at":"2026-07-01T01:17:42.332293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17917","created_at":"2026-07-01T01:17:42.332293+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUESBE3GOZYK","created_at":"2026-07-01T01:17:42.332293+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUESBE3GOZYKYTG7","created_at":"2026-07-01T01:17:42.332293+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUESBE3G","created_at":"2026-07-01T01:17:42.332293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.24192","citing_title":"Co-occurring associated retained concepts in Diffusion Unlearning","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30825","citing_title":"Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI","json":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI.json","graph_json":"https://pith.science/api/pith-number/NUESBE3GOZYKYTG7OFKBEAVPTI/graph.json","events_json":"https://pith.science/api/pith-number/NUESBE3GOZYKYTG7OFKBEAVPTI/events.json","paper":"https://pith.science/paper/NUESBE3G"},"agent_actions":{"view_html":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI","download_json":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI.json","view_paper":"https://pith.science/paper/NUESBE3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.17917&json=true","fetch_graph":"https://pith.science/api/pith-number/NUESBE3GOZYKYTG7OFKBEAVPTI/graph.json","fetch_events":"https://pith.science/api/pith-number/NUESBE3GOZYKYTG7OFKBEAVPTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI/action/storage_attestation","attest_author":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI/action/author_attestation","sign_citation":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI/action/citation_signature","submit_replication":"https://pith.science/pith/NUESBE3GOZYKYTG7OFKBEAVPTI/action/replication_record"}},"created_at":"2026-07-01T01:17:42.332293+00:00","updated_at":"2026-07-01T01:17:42.332293+00:00"}