{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F43XOTZT4AWHM5AIGMOPU7KIIH","short_pith_number":"pith:F43XOTZT","schema_version":"1.0","canonical_sha256":"2f37774f33e02c767408331cfa7d4841d087c14838d91a835d93a1f99d5ea6fa","source":{"kind":"arxiv","id":"2605.26756","version":1},"attestation_state":"computed","paper":{"title":"Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gwangho Kim, Sungyoon Lee","submitted_at":"2026-05-26T09:28:43Z","abstract_excerpt":"Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorization, they often rely on global or model-specific signals and provide limited insight into where memorization appears within a generated image. We provide a geometric characterization of local memorization as a coordinate-wise variance collapse. However, such collapse can also arise from intrinsic data constraints rather than overfitting. To isolate overfitting-driven memorization, we propose curvature-difference methods that subtract the curvatu"},"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":"2605.26756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"e1fc260e79e21c853711892efb7ae0e4cd467366332133c7552aa024fec680c1","abstract_canon_sha256":"2235bb62adbdb41e7ad11b2ad53692d6ed99ab5741469ae5a4ca810eb184910e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:11.003839Z","signature_b64":"3qvwiePMP8l/7I8yGlERQk0p2SILNGp1M1hqZ3Ou2bt2zVSr95l/bgDe9OgEWe7A66hkXH7OY4JlybAVtxOVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f37774f33e02c767408331cfa7d4841d087c14838d91a835d93a1f99d5ea6fa","last_reissued_at":"2026-05-27T01:06:11.002955Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:11.002955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gwangho Kim, Sungyoon Lee","submitted_at":"2026-05-26T09:28:43Z","abstract_excerpt":"Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorization, they often rely on global or model-specific signals and provide limited insight into where memorization appears within a generated image. We provide a geometric characterization of local memorization as a coordinate-wise variance collapse. However, such collapse can also arise from intrinsic data constraints rather than overfitting. To isolate overfitting-driven memorization, we propose curvature-difference methods that subtract the curvatu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26756","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/2605.26756/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":"2605.26756","created_at":"2026-05-27T01:06:11.003100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26756v1","created_at":"2026-05-27T01:06:11.003100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26756","created_at":"2026-05-27T01:06:11.003100+00:00"},{"alias_kind":"pith_short_12","alias_value":"F43XOTZT4AWH","created_at":"2026-05-27T01:06:11.003100+00:00"},{"alias_kind":"pith_short_16","alias_value":"F43XOTZT4AWHM5AI","created_at":"2026-05-27T01:06:11.003100+00:00"},{"alias_kind":"pith_short_8","alias_value":"F43XOTZT","created_at":"2026-05-27T01:06:11.003100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH","json":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH.json","graph_json":"https://pith.science/api/pith-number/F43XOTZT4AWHM5AIGMOPU7KIIH/graph.json","events_json":"https://pith.science/api/pith-number/F43XOTZT4AWHM5AIGMOPU7KIIH/events.json","paper":"https://pith.science/paper/F43XOTZT"},"agent_actions":{"view_html":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH","download_json":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH.json","view_paper":"https://pith.science/paper/F43XOTZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26756&json=true","fetch_graph":"https://pith.science/api/pith-number/F43XOTZT4AWHM5AIGMOPU7KIIH/graph.json","fetch_events":"https://pith.science/api/pith-number/F43XOTZT4AWHM5AIGMOPU7KIIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH/action/storage_attestation","attest_author":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH/action/author_attestation","sign_citation":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH/action/citation_signature","submit_replication":"https://pith.science/pith/F43XOTZT4AWHM5AIGMOPU7KIIH/action/replication_record"}},"created_at":"2026-05-27T01:06:11.003100+00:00","updated_at":"2026-05-27T01:06:11.003100+00:00"}