{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:THCZLJGYRNG7MDFS75I7KBATCM","short_pith_number":"pith:THCZLJGY","canonical_record":{"source":{"id":"2605.16415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:45:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8cc0610c1ed2af11428580bbae66adaff17bedf05668d8ea333e0d3f2336e5f","abstract_canon_sha256":"be772f5793a40f693c3d661fbf7ae317e6e5476e88786bec58e5c0f02e7aa1bf"},"schema_version":"1.0"},"canonical_sha256":"99c595a4d88b4df60cb2ff51f5041313211b0c87441fab5f6e1b64a168f4e207","source":{"kind":"arxiv","id":"2605.16415","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16415","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16415v1","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16415","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"THCZLJGYRNG7","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"THCZLJGYRNG7MDFS","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"THCZLJGY","created_at":"2026-05-20T00:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:THCZLJGYRNG7MDFS75I7KBATCM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:45:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8cc0610c1ed2af11428580bbae66adaff17bedf05668d8ea333e0d3f2336e5f","abstract_canon_sha256":"be772f5793a40f693c3d661fbf7ae317e6e5476e88786bec58e5c0f02e7aa1bf"},"schema_version":"1.0"},"canonical_sha256":"99c595a4d88b4df60cb2ff51f5041313211b0c87441fab5f6e1b64a168f4e207","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:21.123200Z","signature_b64":"xInUideq6cNyPtpFZYk/rda9Zg70T1HfyOuPDU1MGKM34nlIYwufAkg2+3zT6cWkYGpM62EaC7mKlG7RQiyrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99c595a4d88b4df60cb2ff51f5041313211b0c87441fab5f6e1b64a168f4e207","last_reissued_at":"2026-05-20T00:02:21.122508Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:21.122508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16415","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mqya9W4RrktVDrhLG34xvppsvTXY0MLkX/gccScEIxDZ1fBLMjIZ+L5RpudAKGuAR0QwyXskDI81Zek0kqXEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:09:33.982447Z"},"content_sha256":"fd6a4e81476de5d373842b191d13305d953513c0f5dab39cc0ec3cd9e04a44cc","schema_version":"1.0","event_id":"sha256:fd6a4e81476de5d373842b191d13305d953513c0f5dab39cc0ec3cd9e04a44cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:THCZLJGYRNG7MDFS75I7KBATCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Models, Denoiser Architecture and Creativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Itamar Levine, Yair Weiss","submitted_at":"2026-05-13T16:45:42Z","abstract_excerpt":"The creativity of diffusion models refers to their ability to generate highly realistic images that are different from their training data. Creativity is somewhat surprising since it is known that if the denoiser used in the diffusion model is the Bayes optimal denoiser for a given training set, then the model will simply copy the training samples. In this paper we present empirical and theoretical results that suggest that creativity in diffusion models is due to an interaction between the denoiser architecture and the target distribution. Theoretically, we give explicit forms for the distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16415","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/2605.16415/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:41:56.563299Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.592449Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e196250783b77f2cc5c1e9417204a6264320e73ca4c9d98b9b79193f3c771dac"},"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":"2026-05-20T00:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKd0c5Xqm2RNtZJxnhXnHCEpm3EhhwwAV4OxzCjB71SOj7M2GP2nTNW1Kp8FHi3wD/UqXFRa4INrHtwni3glBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:09:33.983226Z"},"content_sha256":"70527f622a5fde4859935d6e89d75d9be7a10f8d4800bb36b14268f5750fbee6","schema_version":"1.0","event_id":"sha256:70527f622a5fde4859935d6e89d75d9be7a10f8d4800bb36b14268f5750fbee6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THCZLJGYRNG7MDFS75I7KBATCM/bundle.json","state_url":"https://pith.science/pith/THCZLJGYRNG7MDFS75I7KBATCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THCZLJGYRNG7MDFS75I7KBATCM/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":"2026-05-25T23:09:33Z","links":{"resolver":"https://pith.science/pith/THCZLJGYRNG7MDFS75I7KBATCM","bundle":"https://pith.science/pith/THCZLJGYRNG7MDFS75I7KBATCM/bundle.json","state":"https://pith.science/pith/THCZLJGYRNG7MDFS75I7KBATCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THCZLJGYRNG7MDFS75I7KBATCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:THCZLJGYRNG7MDFS75I7KBATCM","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":"be772f5793a40f693c3d661fbf7ae317e6e5476e88786bec58e5c0f02e7aa1bf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:45:42Z","title_canon_sha256":"d8cc0610c1ed2af11428580bbae66adaff17bedf05668d8ea333e0d3f2336e5f"},"schema_version":"1.0","source":{"id":"2605.16415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16415","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16415v1","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16415","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"THCZLJGYRNG7","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"THCZLJGYRNG7MDFS","created_at":"2026-05-20T00:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"THCZLJGY","created_at":"2026-05-20T00:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:70527f622a5fde4859935d6e89d75d9be7a10f8d4800bb36b14268f5750fbee6","target":"graph","created_at":"2026-05-20T00:02:21Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:41:56.563299Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.592449Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16415/integrity.json","findings":[],"snapshot_sha256":"e196250783b77f2cc5c1e9417204a6264320e73ca4c9d98b9b79193f3c771dac","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The creativity of diffusion models refers to their ability to generate highly realistic images that are different from their training data. Creativity is somewhat surprising since it is known that if the denoiser used in the diffusion model is the Bayes optimal denoiser for a given training set, then the model will simply copy the training samples. In this paper we present empirical and theoretical results that suggest that creativity in diffusion models is due to an interaction between the denoiser architecture and the target distribution. Theoretically, we give explicit forms for the distrib","authors_text":"Itamar Levine, Yair Weiss","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:45:42Z","title":"Diffusion Models, Denoiser Architecture and Creativity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16415","kind":"arxiv","version":1},"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:fd6a4e81476de5d373842b191d13305d953513c0f5dab39cc0ec3cd9e04a44cc","target":"record","created_at":"2026-05-20T00:02:21Z","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":"be772f5793a40f693c3d661fbf7ae317e6e5476e88786bec58e5c0f02e7aa1bf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:45:42Z","title_canon_sha256":"d8cc0610c1ed2af11428580bbae66adaff17bedf05668d8ea333e0d3f2336e5f"},"schema_version":"1.0","source":{"id":"2605.16415","kind":"arxiv","version":1}},"canonical_sha256":"99c595a4d88b4df60cb2ff51f5041313211b0c87441fab5f6e1b64a168f4e207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99c595a4d88b4df60cb2ff51f5041313211b0c87441fab5f6e1b64a168f4e207","first_computed_at":"2026-05-20T00:02:21.122508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:21.122508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xInUideq6cNyPtpFZYk/rda9Zg70T1HfyOuPDU1MGKM34nlIYwufAkg2+3zT6cWkYGpM62EaC7mKlG7RQiyrBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:21.123200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd6a4e81476de5d373842b191d13305d953513c0f5dab39cc0ec3cd9e04a44cc","sha256:70527f622a5fde4859935d6e89d75d9be7a10f8d4800bb36b14268f5750fbee6"],"state_sha256":"53d33157aa57bf6252fc5730a2977eb447a40aec11fa940fc3d61f162e475037"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XwG4fZ6IG8QDNmC5ILxrd4TTVWCtymyP8OB2lRPl8fBGRM7t17Np0zAMJTvDhAZHEHvXB1yj3hV3L/zN45PjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:09:33.987029Z","bundle_sha256":"9c9b024e6066be5f56d94738a474c39f58c5ba09bd22e642d747c627db1df56d"}}