{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F2TG32DVJZYW7ZKRJWXFI4WV4B","short_pith_number":"pith:F2TG32DV","canonical_record":{"source":{"id":"2407.01014","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T07:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"d4cf3ba2061999d9e3d539b6d61bc7857b18704f2051ab0df3a32378a20f3605","abstract_canon_sha256":"dc3b94a282f5f31d517cf29c347f91017cb63249d4b4f72d56331bb23d4cc8d7"},"schema_version":"1.0"},"canonical_sha256":"2ea66de8754e716fe5514dae5472d5e06fac1722ab86257023b780ae60f72662","source":{"kind":"arxiv","id":"2407.01014","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01014","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01014v2","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01014","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"F2TG32DVJZYW","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"F2TG32DVJZYW7ZKR","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"F2TG32DV","created_at":"2026-06-29T01:14:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F2TG32DVJZYW7ZKRJWXFI4WV4B","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01014","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T07:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"d4cf3ba2061999d9e3d539b6d61bc7857b18704f2051ab0df3a32378a20f3605","abstract_canon_sha256":"dc3b94a282f5f31d517cf29c347f91017cb63249d4b4f72d56331bb23d4cc8d7"},"schema_version":"1.0"},"canonical_sha256":"2ea66de8754e716fe5514dae5472d5e06fac1722ab86257023b780ae60f72662","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:00.532931Z","signature_b64":"CwAUQclz84nyFxQT9f1cEEhNi/Nvi5ddD+pVwAfmwqgc3vofBmOrNa2GjkD/Li43oINQyBRbYWaDO1XyRgKzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea66de8754e716fe5514dae5472d5e06fac1722ab86257023b780ae60f72662","last_reissued_at":"2026-06-29T01:14:00.532461Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:00.532461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01014","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":"2026-06-29T01:14:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eE99n3FkghPZw3d3SnQuxVbUuWGhBNiNC4H3OAPL4Fluy2rBzWbQm/+AXo9VeCKVjz5tvQyYiBRVJbZHI7neDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T05:37:46.681530Z"},"content_sha256":"8dd2182c39de8cce2bd6e8715ff3083b41717a5ff38cc3f5d9c135976e48e8e4","schema_version":"1.0","event_id":"sha256:8dd2182c39de8cce2bd6e8715ff3083b41717a5ff38cc3f5d9c135976e48e8e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F2TG32DVJZYW7ZKRJWXFI4WV4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weimin Bai, Wenzheng Chen, Yifei Wang","submitted_at":"2024-07-01T07:00:17Z","abstract_excerpt":"Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations. Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step). This iterative process leads the learned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01014","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/2407.01014/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":"2026-06-29T01:14:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdDBbakeYnKdN6AZM+mdqwYRVVIWlD07Ff0fF7xRyEQSYoDItd0Og2MwwkEsQTJHP1WaMYwNRcKximAqe/UCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T05:37:46.682192Z"},"content_sha256":"45718bf44777ed8836a0f050e23b82727472c01beff9d89c02378f82db8def4b","schema_version":"1.0","event_id":"sha256:45718bf44777ed8836a0f050e23b82727472c01beff9d89c02378f82db8def4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B/bundle.json","state_url":"https://pith.science/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B/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":"2026-06-30T05:37:46Z","links":{"resolver":"https://pith.science/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B","bundle":"https://pith.science/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B/bundle.json","state":"https://pith.science/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2TG32DVJZYW7ZKRJWXFI4WV4B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2TG32DVJZYW7ZKRJWXFI4WV4B","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":"dc3b94a282f5f31d517cf29c347f91017cb63249d4b4f72d56331bb23d4cc8d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T07:00:17Z","title_canon_sha256":"d4cf3ba2061999d9e3d539b6d61bc7857b18704f2051ab0df3a32378a20f3605"},"schema_version":"1.0","source":{"id":"2407.01014","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01014","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01014v2","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01014","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"F2TG32DVJZYW","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"F2TG32DVJZYW7ZKR","created_at":"2026-06-29T01:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"F2TG32DV","created_at":"2026-06-29T01:14:00Z"}],"graph_snapshots":[{"event_id":"sha256:45718bf44777ed8836a0f050e23b82727472c01beff9d89c02378f82db8def4b","target":"graph","created_at":"2026-06-29T01:14:00Z","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/2407.01014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations. Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step). This iterative process leads the learned ","authors_text":"He Sun, Weimin Bai, Wenzheng Chen, Yifei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T07:00:17Z","title":"An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01014","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":"sha256:8dd2182c39de8cce2bd6e8715ff3083b41717a5ff38cc3f5d9c135976e48e8e4","target":"record","created_at":"2026-06-29T01:14:00Z","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":"dc3b94a282f5f31d517cf29c347f91017cb63249d4b4f72d56331bb23d4cc8d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T07:00:17Z","title_canon_sha256":"d4cf3ba2061999d9e3d539b6d61bc7857b18704f2051ab0df3a32378a20f3605"},"schema_version":"1.0","source":{"id":"2407.01014","kind":"arxiv","version":2}},"canonical_sha256":"2ea66de8754e716fe5514dae5472d5e06fac1722ab86257023b780ae60f72662","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ea66de8754e716fe5514dae5472d5e06fac1722ab86257023b780ae60f72662","first_computed_at":"2026-06-29T01:14:00.532461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:00.532461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CwAUQclz84nyFxQT9f1cEEhNi/Nvi5ddD+pVwAfmwqgc3vofBmOrNa2GjkD/Li43oINQyBRbYWaDO1XyRgKzBg==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:00.532931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01014","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dd2182c39de8cce2bd6e8715ff3083b41717a5ff38cc3f5d9c135976e48e8e4","sha256:45718bf44777ed8836a0f050e23b82727472c01beff9d89c02378f82db8def4b"],"state_sha256":"d0804cd582f0043cce67dcca878043a2cf8ed724596155ef1de244753f21d1d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJ9uXSXmtbwbyjQUMBIrMRlukF9tkZJ8ZCGiPGdCK+Hkm29eDMno4aKxeD4r36pZ0eKYQASA+3QBYdRgrOoBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T05:37:46.685246Z","bundle_sha256":"f8317cc5425530a9393faaa1b905acec90b97a46e11eeb7cb1c821b88279b6f4"}}