{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AELZZWLF4VB3CCASWMC23JXWIE","short_pith_number":"pith:AELZZWLF","schema_version":"1.0","canonical_sha256":"01179cd965e543b10812b305ada6f64124930e1e8cd8c10ca76ff276e5f32164","source":{"kind":"arxiv","id":"2310.11142","version":2},"attestation_state":"computed","paper":{"title":"BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Dequan Wang, Lei Gan, Siqi Kou, Zhijie Deng","submitted_at":"2023-10-17T10:45:28Z","abstract_excerpt":"Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper sample-wise metric. To address this, we propose BayesDiff, a pixel-wise uncertainty estimator for generations from diffusion models based on Bayesian inference. In particular, we derive a novel uncertainty iteration principle to characterize the uncertainty dynamics in diffusion, and leverage the last-layer Laplace approximation for efficient Bayesian inference. The estimated pixel-wise uncertainty can not only be aggreg"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.11142","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-17T10:45:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c4da68c9c89eb21cea8feee9fbf832aaf55a30c3072921366054dafc4a25bb5","abstract_canon_sha256":"933f9cb33a3e61e57fc24295cb14744fc1df222a3ec44fc9e061af15b234eaf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:34.093041Z","signature_b64":"bjLKs/O9PFCwObURyGnHZ3HrEfEbPnkXnRJDoqGl0/JPJQNBzJM+USothWB/slBpYu2eElZNTUF2oKIou7QNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01179cd965e543b10812b305ada6f64124930e1e8cd8c10ca76ff276e5f32164","last_reissued_at":"2026-07-05T07:51:34.092549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:34.092549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Dequan Wang, Lei Gan, Siqi Kou, Zhijie Deng","submitted_at":"2023-10-17T10:45:28Z","abstract_excerpt":"Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper sample-wise metric. To address this, we propose BayesDiff, a pixel-wise uncertainty estimator for generations from diffusion models based on Bayesian inference. In particular, we derive a novel uncertainty iteration principle to characterize the uncertainty dynamics in diffusion, and leverage the last-layer Laplace approximation for efficient Bayesian inference. The estimated pixel-wise uncertainty can not only be aggreg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11142","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/2310.11142/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.11142","created_at":"2026-07-05T07:51:34.092607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11142v2","created_at":"2026-07-05T07:51:34.092607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11142","created_at":"2026-07-05T07:51:34.092607+00:00"},{"alias_kind":"pith_short_12","alias_value":"AELZZWLF4VB3","created_at":"2026-07-05T07:51:34.092607+00:00"},{"alias_kind":"pith_short_16","alias_value":"AELZZWLF4VB3CCAS","created_at":"2026-07-05T07:51:34.092607+00:00"},{"alias_kind":"pith_short_8","alias_value":"AELZZWLF","created_at":"2026-07-05T07:51:34.092607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01595","citing_title":"Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00941","citing_title":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21717","citing_title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00941","citing_title":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21717","citing_title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00941","citing_title":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE","json":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE.json","graph_json":"https://pith.science/api/pith-number/AELZZWLF4VB3CCASWMC23JXWIE/graph.json","events_json":"https://pith.science/api/pith-number/AELZZWLF4VB3CCASWMC23JXWIE/events.json","paper":"https://pith.science/paper/AELZZWLF"},"agent_actions":{"view_html":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE","download_json":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE.json","view_paper":"https://pith.science/paper/AELZZWLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11142&json=true","fetch_graph":"https://pith.science/api/pith-number/AELZZWLF4VB3CCASWMC23JXWIE/graph.json","fetch_events":"https://pith.science/api/pith-number/AELZZWLF4VB3CCASWMC23JXWIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE/action/storage_attestation","attest_author":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE/action/author_attestation","sign_citation":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE/action/citation_signature","submit_replication":"https://pith.science/pith/AELZZWLF4VB3CCASWMC23JXWIE/action/replication_record"}},"created_at":"2026-07-05T07:51:34.092607+00:00","updated_at":"2026-07-05T07:51:34.092607+00:00"}