{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SRNAKZCFR5SREGGZI54NQIMSFI","short_pith_number":"pith:SRNAKZCF","schema_version":"1.0","canonical_sha256":"945a0564458f651218d94778d821922a10425126fbabb0c6054d2f9789797b7c","source":{"kind":"arxiv","id":"2309.16948","version":3},"attestation_state":"computed","paper":{"title":"Denoising Diffusion Bridge Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aaron Lou, Linqi Zhou, Samar Khanna, Stefano Ermon","submitted_at":"2023-09-29T03:24:24Z","abstract_excerpt":"Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes from a distribution that is not random noise. As such, diffusion models must rely on cumbersome methods like guidance or projected sampling to incorporate this information in the generative process. In our work, we propose Denoising Diffusion Bridge Models (DDBMs), a natural alternative to this paradigm based on diffusion bridges, a family of processes that interpolate between two paired distributions given as endpoints. "},"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":"2309.16948","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T03:24:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae054a081de19f600b0787c42c04ee637661b5b1f7443a53e1d7702414a6a182","abstract_canon_sha256":"0693b0676ffd4a001bf26e3b13ab83c4cc91646ae4b0fc582ce56a89de854a4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:11.255434Z","signature_b64":"RCNCeOb/U0laLueiT/dWoo2yUb6fKIgnclgcOE4V7njzrMqQOYOaVzEPjmaKv+O8iXkN58WYIfD+ESlorbdwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"945a0564458f651218d94778d821922a10425126fbabb0c6054d2f9789797b7c","last_reissued_at":"2026-07-05T07:20:11.254931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:11.254931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Diffusion Bridge Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aaron Lou, Linqi Zhou, Samar Khanna, Stefano Ermon","submitted_at":"2023-09-29T03:24:24Z","abstract_excerpt":"Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes from a distribution that is not random noise. As such, diffusion models must rely on cumbersome methods like guidance or projected sampling to incorporate this information in the generative process. In our work, we propose Denoising Diffusion Bridge Models (DDBMs), a natural alternative to this paradigm based on diffusion bridges, a family of processes that interpolate between two paired distributions given as endpoints. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16948","kind":"arxiv","version":3},"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/2309.16948/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":"2309.16948","created_at":"2026-07-05T07:20:11.254993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16948v3","created_at":"2026-07-05T07:20:11.254993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16948","created_at":"2026-07-05T07:20:11.254993+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRNAKZCFR5SR","created_at":"2026-07-05T07:20:11.254993+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRNAKZCFR5SREGGZ","created_at":"2026-07-05T07:20:11.254993+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRNAKZCF","created_at":"2026-07-05T07:20:11.254993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22216","citing_title":"Delta-Diffusion: Modeling Longitudinal Brain Amyloid-PET Trajectories via Conditional Poisson Diffusion Bridge","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29934","citing_title":"RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29920","citing_title":"Midpoint Generative Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21717","citing_title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18991","citing_title":"Fast Kernel-Space Diffusion for Remote Sensing Pansharpening","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04678","citing_title":"ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21717","citing_title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27443","citing_title":"ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08976","citing_title":"Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26065","citing_title":"FlowS: One-Step Motion Prediction via Local Transport Conditioning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01568","citing_title":"Unifying Deep Stochastic Processes for Image Enhancement","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05889","citing_title":"DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04924","citing_title":"Your Pre-trained Diffusion Model Secretly Knows Restoration","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05673","citing_title":"Rectified Schr\\\"odinger Bridge Matching for Few-Step Visual Navigation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI","json":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI.json","graph_json":"https://pith.science/api/pith-number/SRNAKZCFR5SREGGZI54NQIMSFI/graph.json","events_json":"https://pith.science/api/pith-number/SRNAKZCFR5SREGGZI54NQIMSFI/events.json","paper":"https://pith.science/paper/SRNAKZCF"},"agent_actions":{"view_html":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI","download_json":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI.json","view_paper":"https://pith.science/paper/SRNAKZCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16948&json=true","fetch_graph":"https://pith.science/api/pith-number/SRNAKZCFR5SREGGZI54NQIMSFI/graph.json","fetch_events":"https://pith.science/api/pith-number/SRNAKZCFR5SREGGZI54NQIMSFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI/action/storage_attestation","attest_author":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI/action/author_attestation","sign_citation":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI/action/citation_signature","submit_replication":"https://pith.science/pith/SRNAKZCFR5SREGGZI54NQIMSFI/action/replication_record"}},"created_at":"2026-07-05T07:20:11.254993+00:00","updated_at":"2026-07-05T07:20:11.254993+00:00"}