{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VR2WV6MD3N2JG3YWZN7LLB7JX5","short_pith_number":"pith:VR2WV6MD","canonical_record":{"source":{"id":"2305.19256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T17:43:33Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"title_canon_sha256":"7df3064a46cceea115a27ffaf2d22d4bdb50f9c49d9205d6f5ba173da55ef500","abstract_canon_sha256":"51ba9867f7bdc7745baba85fbdc88af48486cff38d902f89be54e1c7f69e91d6"},"schema_version":"1.0"},"canonical_sha256":"ac756af983db74936f16cb7eb587e9bf466b2f606ac313a169e242973cb7f900","source":{"kind":"arxiv","id":"2305.19256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19256","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19256v1","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19256","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"VR2WV6MD3N2J","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"VR2WV6MD3N2JG3YW","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"VR2WV6MD","created_at":"2026-07-05T06:15:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VR2WV6MD3N2JG3YWZN7LLB7JX5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T17:43:33Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"title_canon_sha256":"7df3064a46cceea115a27ffaf2d22d4bdb50f9c49d9205d6f5ba173da55ef500","abstract_canon_sha256":"51ba9867f7bdc7745baba85fbdc88af48486cff38d902f89be54e1c7f69e91d6"},"schema_version":"1.0"},"canonical_sha256":"ac756af983db74936f16cb7eb587e9bf466b2f606ac313a169e242973cb7f900","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:40.092543Z","signature_b64":"7pKNGEvsqZMYF+e/4ksoKiL7rF99Z0MkcY9Gw1dVMdv+tNnt0QZ33v4rTweteiahl53wQlNY1ut0n1wS6ksCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac756af983db74936f16cb7eb587e9bf466b2f606ac313a169e242973cb7f900","last_reissued_at":"2026-07-05T06:15:40.092054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:40.092054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19256","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":"2026-07-05T06:15:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEVE8pjv8qvK7Pn+VjYrFT4bURD9VbWrWfZhXWK4vyFCRdszts4b0z70QX+4/CMfwpCUZRdF5S+gyT/eG0jjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:37:58.317694Z"},"content_sha256":"311e13cba817e5e9fbf2e7613aceec01c1b3d95a06cca362f0202c2577c87fc9","schema_version":"1.0","event_id":"sha256:311e13cba817e5e9fbf2e7613aceec01c1b3d95a06cca362f0202c2577c87fc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VR2WV6MD3N2JG3YWZN7LLB7JX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Alexandros G. Dimakis, Aravind Gollakota, Giannis Daras, Kulin Shah, Yuval Dagan","submitted_at":"2023-05-30T17:43:33Z","abstract_excerpt":"We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to acquire. Another benefit of our approach is the ability to train generative models that are less likely to memorize individual training samples since they never observe clean training data. Our main idea is to introduce additional measurement distortion during the diffusion process and require the model to predict the original corrupted image from the further co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19256","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/2305.19256/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":"2026-07-05T06:15:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hLTMlxzIY/OeQwr0UGsp8y+VL5Z6WGf9KNOhA6cylWOCTgb8R0OZgOiGNxLQvPKPRB1PKTq5aZ26HZsAZgXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:37:58.318238Z"},"content_sha256":"8830618a75a9b7c9d57b078f2b8f24f4a09eeb4c62322646fa13ef4328704bf3","schema_version":"1.0","event_id":"sha256:8830618a75a9b7c9d57b078f2b8f24f4a09eeb4c62322646fa13ef4328704bf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5/bundle.json","state_url":"https://pith.science/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5/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":"2026-08-19T09:37:58Z","links":{"resolver":"https://pith.science/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5","bundle":"https://pith.science/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5/bundle.json","state":"https://pith.science/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VR2WV6MD3N2JG3YWZN7LLB7JX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VR2WV6MD3N2JG3YWZN7LLB7JX5","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":"51ba9867f7bdc7745baba85fbdc88af48486cff38d902f89be54e1c7f69e91d6","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T17:43:33Z","title_canon_sha256":"7df3064a46cceea115a27ffaf2d22d4bdb50f9c49d9205d6f5ba173da55ef500"},"schema_version":"1.0","source":{"id":"2305.19256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19256","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19256v1","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19256","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"VR2WV6MD3N2J","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"VR2WV6MD3N2JG3YW","created_at":"2026-07-05T06:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"VR2WV6MD","created_at":"2026-07-05T06:15:40Z"}],"graph_snapshots":[{"event_id":"sha256:8830618a75a9b7c9d57b078f2b8f24f4a09eeb4c62322646fa13ef4328704bf3","target":"graph","created_at":"2026-07-05T06:15:40Z","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/2305.19256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to acquire. Another benefit of our approach is the ability to train generative models that are less likely to memorize individual training samples since they never observe clean training data. Our main idea is to introduce additional measurement distortion during the diffusion process and require the model to predict the original corrupted image from the further co","authors_text":"Adam Klivans, Alexandros G. Dimakis, Aravind Gollakota, Giannis Daras, Kulin Shah, Yuval Dagan","cross_cats":["cs.AI","cs.CV","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T17:43:33Z","title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19256","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":"sha256:311e13cba817e5e9fbf2e7613aceec01c1b3d95a06cca362f0202c2577c87fc9","target":"record","created_at":"2026-07-05T06:15:40Z","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":"51ba9867f7bdc7745baba85fbdc88af48486cff38d902f89be54e1c7f69e91d6","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T17:43:33Z","title_canon_sha256":"7df3064a46cceea115a27ffaf2d22d4bdb50f9c49d9205d6f5ba173da55ef500"},"schema_version":"1.0","source":{"id":"2305.19256","kind":"arxiv","version":1}},"canonical_sha256":"ac756af983db74936f16cb7eb587e9bf466b2f606ac313a169e242973cb7f900","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac756af983db74936f16cb7eb587e9bf466b2f606ac313a169e242973cb7f900","first_computed_at":"2026-07-05T06:15:40.092054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:40.092054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7pKNGEvsqZMYF+e/4ksoKiL7rF99Z0MkcY9Gw1dVMdv+tNnt0QZ33v4rTweteiahl53wQlNY1ut0n1wS6ksCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:40.092543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:311e13cba817e5e9fbf2e7613aceec01c1b3d95a06cca362f0202c2577c87fc9","sha256:8830618a75a9b7c9d57b078f2b8f24f4a09eeb4c62322646fa13ef4328704bf3"],"state_sha256":"81c47b916dc533cd0a425b70d8084ce176a9d8a90fce6b3d24785dee7fd31edc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbhdepKpZD9lYbb1qIj4iEZwWGV4ZOZXg2ngKPgv7LaY+6/EBB81ACFvqNjAwm6UfZpKHZPV0UqYZx/eel4AAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:37:58.322438Z","bundle_sha256":"5b693affa93af4315aa65109cd084efa6cbe192705e70d7449df62ac92ab1db8"}}