{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TJIOWTUPH2C6PUMEMXL5RA7IKR","short_pith_number":"pith:TJIOWTUP","schema_version":"1.0","canonical_sha256":"9a50eb4e8f3e85e7d18465d7d883e8546b4dae1d322d332ff9993eae9a294c2a","source":{"kind":"arxiv","id":"2511.18471","version":3},"attestation_state":"computed","paper":{"title":"Jacobian-Aware Posterior Sampling for Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liav Hen, Raja Giryes, Shady Abu-Hussein, Tom Tirer","submitted_at":"2025-11-23T14:37:59Z","abstract_excerpt":"Diffusion models provide powerful generative priors for solving inverse problems by sampling from a posterior distribution conditioned on corrupted measurements. Existing methods primarily follow two paradigms: direct methods, which approximate the likelihood term, and proximal methods, which incorporate intermediate solutions satisfying measurement constraints into the sampling process. Under standard Gaussian approximations and locally-linear measurements, we demonstrate that these approaches differ fundamentally in their treatment of the diffusion denoiser's Jacobian within the likelihood t"},"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":"2511.18471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T14:37:59Z","cross_cats_sorted":[],"title_canon_sha256":"d53ae79d4bf8a72b46f2582dfd16abbf9d0a1a8a86dd71c2d1cfc3c65ec03eeb","abstract_canon_sha256":"12e8ee4ca2eb40e5ff400ca76b7247eef5767da58fe7adaecce9bf9407bec95c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:18.710354Z","signature_b64":"1Rm0pCWXEDnt1VRwe20hLM1A30HN5YqOR0vRKnOzWUZwmj3JnI+L4NyJoXra7f1gyAwTPE0PQ5fuSi1G9cqmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a50eb4e8f3e85e7d18465d7d883e8546b4dae1d322d332ff9993eae9a294c2a","last_reissued_at":"2026-06-23T02:13:18.709886Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:18.709886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jacobian-Aware Posterior Sampling for Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liav Hen, Raja Giryes, Shady Abu-Hussein, Tom Tirer","submitted_at":"2025-11-23T14:37:59Z","abstract_excerpt":"Diffusion models provide powerful generative priors for solving inverse problems by sampling from a posterior distribution conditioned on corrupted measurements. Existing methods primarily follow two paradigms: direct methods, which approximate the likelihood term, and proximal methods, which incorporate intermediate solutions satisfying measurement constraints into the sampling process. Under standard Gaussian approximations and locally-linear measurements, we demonstrate that these approaches differ fundamentally in their treatment of the diffusion denoiser's Jacobian within the likelihood t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18471","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/2511.18471/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":"2511.18471","created_at":"2026-06-23T02:13:18.709945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.18471v3","created_at":"2026-06-23T02:13:18.709945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18471","created_at":"2026-06-23T02:13:18.709945+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJIOWTUPH2C6","created_at":"2026-06-23T02:13:18.709945+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJIOWTUPH2C6PUME","created_at":"2026-06-23T02:13:18.709945+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJIOWTUP","created_at":"2026-06-23T02:13:18.709945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.26592","citing_title":"Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse Problems","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14267","citing_title":"Image Restoration via Diffusion Models with Dynamic Resolution","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR","json":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR.json","graph_json":"https://pith.science/api/pith-number/TJIOWTUPH2C6PUMEMXL5RA7IKR/graph.json","events_json":"https://pith.science/api/pith-number/TJIOWTUPH2C6PUMEMXL5RA7IKR/events.json","paper":"https://pith.science/paper/TJIOWTUP"},"agent_actions":{"view_html":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR","download_json":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR.json","view_paper":"https://pith.science/paper/TJIOWTUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.18471&json=true","fetch_graph":"https://pith.science/api/pith-number/TJIOWTUPH2C6PUMEMXL5RA7IKR/graph.json","fetch_events":"https://pith.science/api/pith-number/TJIOWTUPH2C6PUMEMXL5RA7IKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR/action/storage_attestation","attest_author":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR/action/author_attestation","sign_citation":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR/action/citation_signature","submit_replication":"https://pith.science/pith/TJIOWTUPH2C6PUMEMXL5RA7IKR/action/replication_record"}},"created_at":"2026-06-23T02:13:18.709945+00:00","updated_at":"2026-06-23T02:13:18.709945+00:00"}