{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BTHAWDFQ3JL3RNIAACGORUH3LN","short_pith_number":"pith:BTHAWDFQ","schema_version":"1.0","canonical_sha256":"0cce0b0cb0da57b8b500008ce8d0fb5b6fb734f82e3d31253930c9f658071838","source":{"kind":"arxiv","id":"2305.04391","version":2},"attestation_state":"computed","paper":{"title":"A Variational Perspective on Solving Inverse Problems with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Jan Kautz, Jiaming Song, Morteza Mardani","submitted_at":"2023-05-07T23:00:47Z","abstract_excerpt":"Diffusion models have emerged as a key pillar of foundation models in visual domains. One of their critical applications is to universally solve different downstream inverse tasks via a single diffusion prior without re-training for each task. Most inverse tasks can be formulated as inferring a posterior distribution over data (e.g., a full image) given a measurement (e.g., a masked image). This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. To cope with this challenge, we propose a variational app"},"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":"2305.04391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-07T23:00:47Z","cross_cats_sorted":["cs.CV","cs.NA","math.NA","stat.ML"],"title_canon_sha256":"0b423f7eb0d686be38b5402fcf4a14e2f70488bae550087e1a5669dfc0786ec9","abstract_canon_sha256":"1bd7972697b5b95ac95b16f3ca7e95e85195f5255d9505e39c787ea8c9c1e6ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:54.561999Z","signature_b64":"NNKxvypPt1H8f0IEz9/R2DHfccTb5C2/QlStIUiVpGhABQ7+jlGQ5XRULi4ZDpnHRoawlZUMwXbq1Ul7uHeIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cce0b0cb0da57b8b500008ce8d0fb5b6fb734f82e3d31253930c9f658071838","last_reissued_at":"2026-07-05T06:55:54.561515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:54.561515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variational Perspective on Solving Inverse Problems with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Jan Kautz, Jiaming Song, Morteza Mardani","submitted_at":"2023-05-07T23:00:47Z","abstract_excerpt":"Diffusion models have emerged as a key pillar of foundation models in visual domains. One of their critical applications is to universally solve different downstream inverse tasks via a single diffusion prior without re-training for each task. Most inverse tasks can be formulated as inferring a posterior distribution over data (e.g., a full image) given a measurement (e.g., a masked image). This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. To cope with this challenge, we propose a variational app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04391","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/2305.04391/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":"2305.04391","created_at":"2026-07-05T06:55:54.561573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04391v2","created_at":"2026-07-05T06:55:54.561573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04391","created_at":"2026-07-05T06:55:54.561573+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTHAWDFQ3JL3","created_at":"2026-07-05T06:55:54.561573+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTHAWDFQ3JL3RNIA","created_at":"2026-07-05T06:55:54.561573+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTHAWDFQ","created_at":"2026-07-05T06:55:54.561573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02331","citing_title":"Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17353","citing_title":"Dual Ascent Diffusion for Inverse Problems","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16344","citing_title":"Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07150","citing_title":"FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20549","citing_title":"Sample-efficient evidence estimation of score based priors for model selection","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07339","citing_title":"Real-Time Execution of Action Chunking Flow Policies","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11506","citing_title":"Principled Design of Diffusion-based Optimizers for Inverse Problems","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03712","citing_title":"Tempered Guided Diffusion","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11375","citing_title":"DiLO: Decoupling Generative Priors and Neural Operators via Diffusion Latent Optimization for Inverse Problems","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN","json":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN.json","graph_json":"https://pith.science/api/pith-number/BTHAWDFQ3JL3RNIAACGORUH3LN/graph.json","events_json":"https://pith.science/api/pith-number/BTHAWDFQ3JL3RNIAACGORUH3LN/events.json","paper":"https://pith.science/paper/BTHAWDFQ"},"agent_actions":{"view_html":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN","download_json":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN.json","view_paper":"https://pith.science/paper/BTHAWDFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04391&json=true","fetch_graph":"https://pith.science/api/pith-number/BTHAWDFQ3JL3RNIAACGORUH3LN/graph.json","fetch_events":"https://pith.science/api/pith-number/BTHAWDFQ3JL3RNIAACGORUH3LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN/action/storage_attestation","attest_author":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN/action/author_attestation","sign_citation":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN/action/citation_signature","submit_replication":"https://pith.science/pith/BTHAWDFQ3JL3RNIAACGORUH3LN/action/replication_record"}},"created_at":"2026-07-05T06:55:54.561573+00:00","updated_at":"2026-07-05T06:55:54.561573+00:00"}