{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5HLJ25ZFPTUB6YXVO4N4TYLNG2","short_pith_number":"pith:5HLJ25ZF","canonical_record":{"source":{"id":"2404.10177","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T14:22:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"392e4c39756cfa4f463dfce188fae0bda37954811c988d86559909c7b85e3377","abstract_canon_sha256":"aad3ab28aa1b2faf0b31daa26bcbf815c86ce9df40779aed326bddc0ee43bc9d"},"schema_version":"1.0"},"canonical_sha256":"e9d69d77257ce81f62f5771bc9e16d36935801fb62fcc1259ffad6979f0d998a","source":{"kind":"arxiv","id":"2404.10177","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10177","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10177v2","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10177","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"pith_short_12","alias_value":"5HLJ25ZFPTUB","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"pith_short_16","alias_value":"5HLJ25ZFPTUB6YXV","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"pith_short_8","alias_value":"5HLJ25ZF","created_at":"2026-07-05T08:46:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5HLJ25ZFPTUB6YXVO4N4TYLNG2","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10177","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T14:22:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"392e4c39756cfa4f463dfce188fae0bda37954811c988d86559909c7b85e3377","abstract_canon_sha256":"aad3ab28aa1b2faf0b31daa26bcbf815c86ce9df40779aed326bddc0ee43bc9d"},"schema_version":"1.0"},"canonical_sha256":"e9d69d77257ce81f62f5771bc9e16d36935801fb62fcc1259ffad6979f0d998a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:54.395733Z","signature_b64":"43ShPKtEizfeVWROkjZPy9lIYov6uAEPgGpXl8uanP+v47gfVnObkhWFTSIXUJXGXltBWpu6QWr1DMwg14jwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d69d77257ce81f62f5771bc9e16d36935801fb62fcc1259ffad6979f0d998a","last_reissued_at":"2026-07-05T08:46:54.395177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:54.395177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10177","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":"2026-07-05T08:46:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nLyuUX22hyjj6QcRSHWJjcfdB+gk790h+Cds42BVliJK03ZzqbK0NYMY5c7j8zkX/WmGCtdPdY0ZemdKqHxVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:15:25.325780Z"},"content_sha256":"31fd9525aa15bef51b17ed6ce729f6046694a8fc48eb5e7a56af0bb98176bbe8","schema_version":"1.0","event_id":"sha256:31fd9525aa15bef51b17ed6ce729f6046694a8fc48eb5e7a56af0bb98176bbe8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5HLJ25ZFPTUB6YXVO4N4TYLNG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros G. Dimakis, Constantinos Daskalakis, Giannis Daras","submitted_at":"2024-03-20T14:22:12Z","abstract_excerpt":"Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data resort to approximations which deteriorate performance. We present the first framework for training diffusion models that provably sample from the uncorrupted distribution given only noisy training data, solving an open problem in this space. Our key technical contribution is a method that uses a double application of Tweedie's formula and a consistency loss function that allows us t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10177","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/2404.10177/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":"2026-07-05T08:46:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rg4uudDddTyNv+vEr4F9r6jlPvaI9dJqtMwFyzdScKu8J8bGl4s3otevLD2avC3ZVexhuOYH7txx2mJnsbItAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:15:25.328036Z"},"content_sha256":"a007a4924f7b1d021c8405b562941cd4d449ff327fac093ab3db5773e02ce80e","schema_version":"1.0","event_id":"sha256:a007a4924f7b1d021c8405b562941cd4d449ff327fac093ab3db5773e02ce80e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2/bundle.json","state_url":"https://pith.science/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2/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":"2026-08-05T11:15:25Z","links":{"resolver":"https://pith.science/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2","bundle":"https://pith.science/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2/bundle.json","state":"https://pith.science/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HLJ25ZFPTUB6YXVO4N4TYLNG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5HLJ25ZFPTUB6YXVO4N4TYLNG2","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":"aad3ab28aa1b2faf0b31daa26bcbf815c86ce9df40779aed326bddc0ee43bc9d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T14:22:12Z","title_canon_sha256":"392e4c39756cfa4f463dfce188fae0bda37954811c988d86559909c7b85e3377"},"schema_version":"1.0","source":{"id":"2404.10177","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10177","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10177v2","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10177","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"pith_short_12","alias_value":"5HLJ25ZFPTUB","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"pith_short_16","alias_value":"5HLJ25ZFPTUB6YXV","created_at":"2026-07-05T08:46:54Z"},{"alias_kind":"pith_short_8","alias_value":"5HLJ25ZF","created_at":"2026-07-05T08:46:54Z"}],"graph_snapshots":[{"event_id":"sha256:a007a4924f7b1d021c8405b562941cd4d449ff327fac093ab3db5773e02ce80e","target":"graph","created_at":"2026-07-05T08:46:54Z","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/2404.10177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data resort to approximations which deteriorate performance. We present the first framework for training diffusion models that provably sample from the uncorrupted distribution given only noisy training data, solving an open problem in this space. Our key technical contribution is a method that uses a double application of Tweedie's formula and a consistency loss function that allows us t","authors_text":"Alexandros G. Dimakis, Constantinos Daskalakis, Giannis Daras","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T14:22:12Z","title":"Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10177","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":"sha256:31fd9525aa15bef51b17ed6ce729f6046694a8fc48eb5e7a56af0bb98176bbe8","target":"record","created_at":"2026-07-05T08:46:54Z","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":"aad3ab28aa1b2faf0b31daa26bcbf815c86ce9df40779aed326bddc0ee43bc9d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T14:22:12Z","title_canon_sha256":"392e4c39756cfa4f463dfce188fae0bda37954811c988d86559909c7b85e3377"},"schema_version":"1.0","source":{"id":"2404.10177","kind":"arxiv","version":2}},"canonical_sha256":"e9d69d77257ce81f62f5771bc9e16d36935801fb62fcc1259ffad6979f0d998a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9d69d77257ce81f62f5771bc9e16d36935801fb62fcc1259ffad6979f0d998a","first_computed_at":"2026-07-05T08:46:54.395177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:54.395177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"43ShPKtEizfeVWROkjZPy9lIYov6uAEPgGpXl8uanP+v47gfVnObkhWFTSIXUJXGXltBWpu6QWr1DMwg14jwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:54.395733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10177","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31fd9525aa15bef51b17ed6ce729f6046694a8fc48eb5e7a56af0bb98176bbe8","sha256:a007a4924f7b1d021c8405b562941cd4d449ff327fac093ab3db5773e02ce80e"],"state_sha256":"059059e12f084df340d891f157f493887ed082eab20eab432ba62ace7172b281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2N5ep/fka+PDC+QdB0+5Z10RU9D/GZh633EoqbdW1jCsZDYDUrA5mLk4CrTp5/M9kZCcETtuGs6bT8dWX8u7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:15:25.343999Z","bundle_sha256":"8517feded262773b79e9e09770058c5673fe1b3ab5e30eca97a4353a267ba306"}}