{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VHTIG2QZ3AYRLSCJ3EWSHPPDWZ","short_pith_number":"pith:VHTIG2QZ","canonical_record":{"source":{"id":"2602.09639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T10:38:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b859d3074e92673374e03c61783cc156bbfaa28fc75d79e01d5383268dd2b1fb","abstract_canon_sha256":"cb8b02a06b323fb338a818d760f5871c0e5c1fb6200fb02cb50ff79112feea75"},"schema_version":"1.0"},"canonical_sha256":"a9e6836a19d83115c849d92d23bde3b66174575a2a7921381929f501cdde4d4f","source":{"kind":"arxiv","id":"2602.09639","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09639","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09639v2","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09639","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"VHTIG2QZ3AYR","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"VHTIG2QZ3AYRLSCJ","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"VHTIG2QZ","created_at":"2026-06-10T01:10:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VHTIG2QZ3AYRLSCJ3EWSHPPDWZ","target":"record","payload":{"canonical_record":{"source":{"id":"2602.09639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T10:38:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b859d3074e92673374e03c61783cc156bbfaa28fc75d79e01d5383268dd2b1fb","abstract_canon_sha256":"cb8b02a06b323fb338a818d760f5871c0e5c1fb6200fb02cb50ff79112feea75"},"schema_version":"1.0"},"canonical_sha256":"a9e6836a19d83115c849d92d23bde3b66174575a2a7921381929f501cdde4d4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:59.350529Z","signature_b64":"ONlReNumHWZJCMQizLEtDiE5CCt41JfvxROzxO+5xlcmdjYsMLR0HVKQUc/OBNU2AU4Mp0ibYHsYcnDANYDfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e6836a19d83115c849d92d23bde3b66174575a2a7921381929f501cdde4d4f","last_reissued_at":"2026-06-10T01:10:59.349521Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:59.349521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.09639","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":"2026-06-10T01:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O117glNoWk9qXA9aHyRYVtgerX3XQjaPNUVMSYFqdLlctF4SEVPHVBNdNttbCR+/4HRV0FJL9axyIkisuOutBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T19:01:06.310152Z"},"content_sha256":"f984bba4278d78272fcd04bc9c595dec59fa1f8bcd9962ab21660e2eb9a560ed","schema_version":"1.0","event_id":"sha256:f984bba4278d78272fcd04bc9c595dec59fa1f8bcd9962ab21660e2eb9a560ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VHTIG2QZ3AYRLSCJ3EWSHPPDWZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Blind denoising diffusion models and the blessings of dimensionality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aram-Alexandre Pooladian, Eero Simoncelli, Sinho Chewi, Zahra Kadkhodaie","submitted_at":"2026-02-10T10:38:16Z","abstract_excerpt":"Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline remain poorly understood. In particular, noise conditioning requires practitioners to incorporate contrived unprincipled noise embeddings into neural network architectures and to use ad hoc noise schedules for sampling. To address these drawbacks, we provide a complete theory for \\emph{blind denoising diffusion models} (BDDMs): a variant of DDMs where the noise amplitude is not passed into the neural network during train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09639","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/2602.09639/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":"2026-06-10T01:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tlZo6z/MfEKpoa7zp1A0Ap7ly532l3p4nrUoYnpO1chMIa6OgNtE9pjXEP8SU68aFAlL3Qlwhvb7Nd5W8BSGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T19:01:06.310556Z"},"content_sha256":"e311bc07902cd4dd58140e4f4ce34f80c0b9c5c7d839a6691860c54c24fdcb55","schema_version":"1.0","event_id":"sha256:e311bc07902cd4dd58140e4f4ce34f80c0b9c5c7d839a6691860c54c24fdcb55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ/bundle.json","state_url":"https://pith.science/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ/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":"2026-06-10T19:01:06Z","links":{"resolver":"https://pith.science/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ","bundle":"https://pith.science/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ/bundle.json","state":"https://pith.science/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHTIG2QZ3AYRLSCJ3EWSHPPDWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VHTIG2QZ3AYRLSCJ3EWSHPPDWZ","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":"cb8b02a06b323fb338a818d760f5871c0e5c1fb6200fb02cb50ff79112feea75","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T10:38:16Z","title_canon_sha256":"b859d3074e92673374e03c61783cc156bbfaa28fc75d79e01d5383268dd2b1fb"},"schema_version":"1.0","source":{"id":"2602.09639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09639","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09639v2","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09639","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"VHTIG2QZ3AYR","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"VHTIG2QZ3AYRLSCJ","created_at":"2026-06-10T01:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"VHTIG2QZ","created_at":"2026-06-10T01:10:59Z"}],"graph_snapshots":[{"event_id":"sha256:e311bc07902cd4dd58140e4f4ce34f80c0b9c5c7d839a6691860c54c24fdcb55","target":"graph","created_at":"2026-06-10T01:10:59Z","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/2602.09639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline remain poorly understood. In particular, noise conditioning requires practitioners to incorporate contrived unprincipled noise embeddings into neural network architectures and to use ad hoc noise schedules for sampling. To address these drawbacks, we provide a complete theory for \\emph{blind denoising diffusion models} (BDDMs): a variant of DDMs where the noise amplitude is not passed into the neural network during train","authors_text":"Aram-Alexandre Pooladian, Eero Simoncelli, Sinho Chewi, Zahra Kadkhodaie","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T10:38:16Z","title":"Blind denoising diffusion models and the blessings of dimensionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09639","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:f984bba4278d78272fcd04bc9c595dec59fa1f8bcd9962ab21660e2eb9a560ed","target":"record","created_at":"2026-06-10T01:10:59Z","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":"cb8b02a06b323fb338a818d760f5871c0e5c1fb6200fb02cb50ff79112feea75","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T10:38:16Z","title_canon_sha256":"b859d3074e92673374e03c61783cc156bbfaa28fc75d79e01d5383268dd2b1fb"},"schema_version":"1.0","source":{"id":"2602.09639","kind":"arxiv","version":2}},"canonical_sha256":"a9e6836a19d83115c849d92d23bde3b66174575a2a7921381929f501cdde4d4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9e6836a19d83115c849d92d23bde3b66174575a2a7921381929f501cdde4d4f","first_computed_at":"2026-06-10T01:10:59.349521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:59.349521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ONlReNumHWZJCMQizLEtDiE5CCt41JfvxROzxO+5xlcmdjYsMLR0HVKQUc/OBNU2AU4Mp0ibYHsYcnDANYDfAg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:59.350529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.09639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f984bba4278d78272fcd04bc9c595dec59fa1f8bcd9962ab21660e2eb9a560ed","sha256:e311bc07902cd4dd58140e4f4ce34f80c0b9c5c7d839a6691860c54c24fdcb55"],"state_sha256":"ad25e87a652d993332837b1b746df41f75adad6bac5d6047e7d983bab7612a3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPCUcrqhVG8EEbtCuiwnPdNsz+CtKIShuG+SwsaTGf4S+RzWwJX7gVtD/n6AgoPFdecgir7PYg2/Kb5Wmub1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T19:01:06.312853Z","bundle_sha256":"45ae49148990030cc6bc62fede0f65a018a20ea85bc1143539cddfc2f2441fab"}}