{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TVUOUMKATJKWAP4T6GFVBG5TM7","short_pith_number":"pith:TVUOUMKA","schema_version":"1.0","canonical_sha256":"9d68ea31409a55603f93f18b509bb367f9170bca5b0aa83de989c12861310130","source":{"kind":"arxiv","id":"2307.08123","version":3},"attestation_state":"computed","paper":{"title":"Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Song, Liyue Shen, Qing Qu, Soo Min Kwon, Xinyu Hu, Zecheng Zhang","submitted_at":"2023-07-16T18:42:01Z","abstract_excerpt":"Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their applicability as priors for high-dimensional real-world data such as medical images. Latent diffusion models, which operate in a much lower-dimensional space, offer a solution to these challenges. However, incorporating latent diffusion models to solve inverse problems remains a challenging problem due to the nonlinearity of the encoder and decoder. To address these i"},"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":"2307.08123","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T18:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"7774dba4494e2dea0d6837c4d6cb1902bb749ab51bb5665adcbf3a6aff0101fc","abstract_canon_sha256":"eba0547eeb009799b4a347e19b891abd0f9eeda0d5f6ca4e1d441d5dba373d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:17.500859Z","signature_b64":"Hrl/9vNyr2vSFI0vvtbliuPkQ3BqhVjbFogX6AjI4LATOUXp19+OlEvPFAq6dp7Mo3vI0rfkF8g+9GJHwRJXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d68ea31409a55603f93f18b509bb367f9170bca5b0aa83de989c12861310130","last_reissued_at":"2026-07-05T08:08:17.500418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:17.500418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Song, Liyue Shen, Qing Qu, Soo Min Kwon, Xinyu Hu, Zecheng Zhang","submitted_at":"2023-07-16T18:42:01Z","abstract_excerpt":"Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their applicability as priors for high-dimensional real-world data such as medical images. Latent diffusion models, which operate in a much lower-dimensional space, offer a solution to these challenges. However, incorporating latent diffusion models to solve inverse problems remains a challenging problem due to the nonlinearity of the encoder and decoder. To address these i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08123","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/2307.08123/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":"2307.08123","created_at":"2026-07-05T08:08:17.500477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08123v3","created_at":"2026-07-05T08:08:17.500477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08123","created_at":"2026-07-05T08:08:17.500477+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVUOUMKATJKW","created_at":"2026-07-05T08:08:17.500477+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVUOUMKATJKWAP4T","created_at":"2026-07-05T08:08:17.500477+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVUOUMKA","created_at":"2026-07-05T08:08:17.500477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27705","citing_title":"AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17603","citing_title":"Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25749","citing_title":"ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-On","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01608","citing_title":"NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23726","citing_title":"q3-MuPa: Quick, Quiet, Quantitative Multi-Parametric MRI using Physics-Informed Diffusion Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09302","citing_title":"Discrete Langevin-Inspired Posterior Sampling","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21960","citing_title":"Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7","json":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7.json","graph_json":"https://pith.science/api/pith-number/TVUOUMKATJKWAP4T6GFVBG5TM7/graph.json","events_json":"https://pith.science/api/pith-number/TVUOUMKATJKWAP4T6GFVBG5TM7/events.json","paper":"https://pith.science/paper/TVUOUMKA"},"agent_actions":{"view_html":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7","download_json":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7.json","view_paper":"https://pith.science/paper/TVUOUMKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08123&json=true","fetch_graph":"https://pith.science/api/pith-number/TVUOUMKATJKWAP4T6GFVBG5TM7/graph.json","fetch_events":"https://pith.science/api/pith-number/TVUOUMKATJKWAP4T6GFVBG5TM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7/action/storage_attestation","attest_author":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7/action/author_attestation","sign_citation":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7/action/citation_signature","submit_replication":"https://pith.science/pith/TVUOUMKATJKWAP4T6GFVBG5TM7/action/replication_record"}},"created_at":"2026-07-05T08:08:17.500477+00:00","updated_at":"2026-07-05T08:08:17.500477+00:00"}