{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XTYU6EUZWRI6EBU2PYG3UUWNUO","short_pith_number":"pith:XTYU6EUZ","canonical_record":{"source":{"id":"2603.13419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"906e7888a176fa0ff84047551e496efad52e274328aab0c8186e993a9dcf080f","abstract_canon_sha256":"09a1eaeaf825a7dc2c0155581590a41c7e1d73a0713b6dc2abfaee4c61d6955d"},"schema_version":"1.0"},"canonical_sha256":"bcf14f1299b451e2069a7e0dba52cda386c3aa8cd71a9373336daaff223821a7","source":{"kind":"arxiv","id":"2603.13419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.13419","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2603.13419v2","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.13419","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"XTYU6EUZWRI6","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"XTYU6EUZWRI6EBU2","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"XTYU6EUZ","created_at":"2026-05-21T01:05:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XTYU6EUZWRI6EBU2PYG3UUWNUO","target":"record","payload":{"canonical_record":{"source":{"id":"2603.13419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"906e7888a176fa0ff84047551e496efad52e274328aab0c8186e993a9dcf080f","abstract_canon_sha256":"09a1eaeaf825a7dc2c0155581590a41c7e1d73a0713b6dc2abfaee4c61d6955d"},"schema_version":"1.0"},"canonical_sha256":"bcf14f1299b451e2069a7e0dba52cda386c3aa8cd71a9373336daaff223821a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:17.690768Z","signature_b64":"Sk2zBuDTP3kXucgMTzHXD66IQ9C97FJ2GtYP230k82OTJdsOvSX7q5NyRscHAi391MbgphPVsc0pWgGjCIsyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf14f1299b451e2069a7e0dba52cda386c3aa8cd71a9373336daaff223821a7","last_reissued_at":"2026-05-21T01:05:17.690176Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:17.690176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.13419","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jHW7y5M6GZuUCTahUMyDsyBSxQeEwOZ9+ekqtxu71E1XDuSOgXrPCC/mOpTnyWlOprLTBod6igQ0XsvQqmECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T08:31:55.171675Z"},"content_sha256":"58c7434741d9020eb5be98f9e8fd95d85dc3183714c28e515bc0071c7e949a67","schema_version":"1.0","event_id":"sha256:58c7434741d9020eb5be98f9e8fd95d85dc3183714c28e515bc0071c7e949a67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XTYU6EUZWRI6EBU2PYG3UUWNUO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Models Memorize in Training -- and Generalize in Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Markus Kollmann, Tim Kaiser","submitted_at":"2026-03-12T21:02:17Z","abstract_excerpt":"Diffusion models generalize well in practice. However, an optimal diffusion model fully memorizes the training data and therefore fails to generalize, raising the question of what induces generalization in a real diffusion model. We show that, despite generalizing at the sample level, diffusion models progressively overfit the denoising training objective and thereby create a generalization gap between the performance on validation and training samples. This gap is most pronounced at intermediate noise levels. Using a fully analytic error-prone toy model, we trace the factors affecting the gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.13419","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/2603.13419/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRXcGWgiHjvrO1jkBjU5xUxcBDSibFDSSpDZcSHOMkWVwqBmNeaYcGMxZ8mE0RuSDutJQNczs3Gkdtp/pUflBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T08:31:55.172442Z"},"content_sha256":"e21c05c3c545c61f73bbbf52a4062410cb278119e707849c40e6dca8c78b2f21","schema_version":"1.0","event_id":"sha256:e21c05c3c545c61f73bbbf52a4062410cb278119e707849c40e6dca8c78b2f21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO/bundle.json","state_url":"https://pith.science/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T08:31:55Z","links":{"resolver":"https://pith.science/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO","bundle":"https://pith.science/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO/bundle.json","state":"https://pith.science/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTYU6EUZWRI6EBU2PYG3UUWNUO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XTYU6EUZWRI6EBU2PYG3UUWNUO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"09a1eaeaf825a7dc2c0155581590a41c7e1d73a0713b6dc2abfaee4c61d6955d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:02:17Z","title_canon_sha256":"906e7888a176fa0ff84047551e496efad52e274328aab0c8186e993a9dcf080f"},"schema_version":"1.0","source":{"id":"2603.13419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.13419","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2603.13419v2","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.13419","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"XTYU6EUZWRI6","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"XTYU6EUZWRI6EBU2","created_at":"2026-05-21T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"XTYU6EUZ","created_at":"2026-05-21T01:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:e21c05c3c545c61f73bbbf52a4062410cb278119e707849c40e6dca8c78b2f21","target":"graph","created_at":"2026-05-21T01:05:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.13419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models generalize well in practice. However, an optimal diffusion model fully memorizes the training data and therefore fails to generalize, raising the question of what induces generalization in a real diffusion model. We show that, despite generalizing at the sample level, diffusion models progressively overfit the denoising training objective and thereby create a generalization gap between the performance on validation and training samples. This gap is most pronounced at intermediate noise levels. Using a fully analytic error-prone toy model, we trace the factors affecting the gen","authors_text":"Markus Kollmann, Tim Kaiser","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.13419","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:58c7434741d9020eb5be98f9e8fd95d85dc3183714c28e515bc0071c7e949a67","target":"record","created_at":"2026-05-21T01:05:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"09a1eaeaf825a7dc2c0155581590a41c7e1d73a0713b6dc2abfaee4c61d6955d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T21:02:17Z","title_canon_sha256":"906e7888a176fa0ff84047551e496efad52e274328aab0c8186e993a9dcf080f"},"schema_version":"1.0","source":{"id":"2603.13419","kind":"arxiv","version":2}},"canonical_sha256":"bcf14f1299b451e2069a7e0dba52cda386c3aa8cd71a9373336daaff223821a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcf14f1299b451e2069a7e0dba52cda386c3aa8cd71a9373336daaff223821a7","first_computed_at":"2026-05-21T01:05:17.690176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:17.690176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sk2zBuDTP3kXucgMTzHXD66IQ9C97FJ2GtYP230k82OTJdsOvSX7q5NyRscHAi391MbgphPVsc0pWgGjCIsyAA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:17.690768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.13419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58c7434741d9020eb5be98f9e8fd95d85dc3183714c28e515bc0071c7e949a67","sha256:e21c05c3c545c61f73bbbf52a4062410cb278119e707849c40e6dca8c78b2f21"],"state_sha256":"c2a99c018be028c10a929dcd26532331bf43506df492473cc6f30aab71fb2559"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jV3s7SGlGz0Vk5fzvySwIOoiBR2BWY1AHSkqxO1umU/LiqKNDUfRDgLgKQcuD5cmjrRChrgakYStkXfuVb0VAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T08:31:55.176194Z","bundle_sha256":"ece68bbcf27ebc779d2b5e2e353649e64835a100ead04968dfbb338aaaf05447"}}