{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P55233CXY3GR7CVDAYAVLULLGN","short_pith_number":"pith:P55233CX","schema_version":"1.0","canonical_sha256":"7f7badec57c6cd1f8aa3060155d16b3369d2300fe68b3007d1eec1ca66e7578e","source":{"kind":"arxiv","id":"2503.08136","version":1},"attestation_state":"computed","paper":{"title":"FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye","submitted_at":"2025-03-11T07:56:14Z","abstract_excerpt":"Flow matching is a recent state-of-the-art framework for generative modeling based on ordinary differential equations (ODEs). While closely related to diffusion models, it provides a more general perspective on generative modeling. Although inverse problem solving has been extensively explored using diffusion models, it has not been rigorously examined within the broader context of flow models. Therefore, here we extend the diffusion inverse solvers (DIS) - which perform posterior sampling by combining a denoising diffusion prior with an likelihood gradient - into the flow framework. Specifica"},"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":"2503.08136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T07:56:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9f3230d97ed14f608e2006a0c3dd870c10fc9ceec0f52959851d14bb1d812c7a","abstract_canon_sha256":"4afaec6a77fcfc71e8200b9fd1d9f3cebb0d7c034200e9acd07ee2bfdddfefe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:51.944211Z","signature_b64":"QjOEkXTAo3uN6LmkSpi7p/pL1lVMNca7H5n7vO+9YGHay9GcN5IHU/Ln/vltLYlsF+Lb1vh6qSv9jSS8/e0JCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f7badec57c6cd1f8aa3060155d16b3369d2300fe68b3007d1eec1ca66e7578e","last_reissued_at":"2026-07-05T10:28:51.943111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:51.943111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye","submitted_at":"2025-03-11T07:56:14Z","abstract_excerpt":"Flow matching is a recent state-of-the-art framework for generative modeling based on ordinary differential equations (ODEs). While closely related to diffusion models, it provides a more general perspective on generative modeling. Although inverse problem solving has been extensively explored using diffusion models, it has not been rigorously examined within the broader context of flow models. Therefore, here we extend the diffusion inverse solvers (DIS) - which perform posterior sampling by combining a denoising diffusion prior with an likelihood gradient - into the flow framework. Specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08136","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/2503.08136/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":"2503.08136","created_at":"2026-07-05T10:28:51.943278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08136v1","created_at":"2026-07-05T10:28:51.943278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08136","created_at":"2026-07-05T10:28:51.943278+00:00"},{"alias_kind":"pith_short_12","alias_value":"P55233CXY3GR","created_at":"2026-07-05T10:28:51.943278+00:00"},{"alias_kind":"pith_short_16","alias_value":"P55233CXY3GR7CVD","created_at":"2026-07-05T10:28:51.943278+00:00"},{"alias_kind":"pith_short_8","alias_value":"P55233CX","created_at":"2026-07-05T10:28:51.943278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26391","citing_title":"Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15418","citing_title":"A General Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18600","citing_title":"Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18365","citing_title":"Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":41,"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}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN","json":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN.json","graph_json":"https://pith.science/api/pith-number/P55233CXY3GR7CVDAYAVLULLGN/graph.json","events_json":"https://pith.science/api/pith-number/P55233CXY3GR7CVDAYAVLULLGN/events.json","paper":"https://pith.science/paper/P55233CX"},"agent_actions":{"view_html":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN","download_json":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN.json","view_paper":"https://pith.science/paper/P55233CX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08136&json=true","fetch_graph":"https://pith.science/api/pith-number/P55233CXY3GR7CVDAYAVLULLGN/graph.json","fetch_events":"https://pith.science/api/pith-number/P55233CXY3GR7CVDAYAVLULLGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN/action/storage_attestation","attest_author":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN/action/author_attestation","sign_citation":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN/action/citation_signature","submit_replication":"https://pith.science/pith/P55233CXY3GR7CVDAYAVLULLGN/action/replication_record"}},"created_at":"2026-07-05T10:28:51.943278+00:00","updated_at":"2026-07-05T10:28:51.943278+00:00"}