{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NKBGOH4ZAC7UXIE7GNUXWPBYCE","short_pith_number":"pith:NKBGOH4Z","schema_version":"1.0","canonical_sha256":"6a82671f9900bf4ba09f33697b3c3811369df069747981bc2357f8d2d68bf790","source":{"kind":"arxiv","id":"2512.18367","version":2},"attestation_state":"computed","paper":{"title":"PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Jinglun Yu, Jin U. Kang, Wenhan Guo, Yaning Wang, Yu Sun","submitted_at":"2025-12-20T13:37:22Z","abstract_excerpt":"Diffusion models are highly expressive image priors for Bayesian inverse problems. However, most diffusion models cannot operate on large-scale, high-dimensional data due to high training and inference costs. In this work, we introduce a Plug-and-play algorithm for 3D stochastic inference with latent diffusion prior (PSI3D) to address massive ($1024\\times 1024\\times 128$) volumes. Specifically, we formulate a Markov chain Monte Carlo approach to reconstruct each two-dimensional (2D) slice by sampling from a 2D latent diffusion model. To enhance inter-slice consistency, we also incorporate tota"},"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":"2512.18367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-12-20T13:37:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5907a67246176e67684e64c7b54b27708d690a95920b50109f8cc8831a19aa38","abstract_canon_sha256":"1bf808a873e3ac3c94350b52e4068689c5f15a21004651d563138c69583dc6c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:16:47.396330Z","signature_b64":"GwPF43cTtYrvE1LOLYWe5BdIE2E3Ap5LS+sL6UKtswu5uJlL3gFirxXJEqQzMR0H9/pKdSGgW5tLdLGL/lWWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a82671f9900bf4ba09f33697b3c3811369df069747981bc2357f8d2d68bf790","last_reissued_at":"2026-08-06T01:16:47.394063Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:16:47.394063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Jinglun Yu, Jin U. Kang, Wenhan Guo, Yaning Wang, Yu Sun","submitted_at":"2025-12-20T13:37:22Z","abstract_excerpt":"Diffusion models are highly expressive image priors for Bayesian inverse problems. However, most diffusion models cannot operate on large-scale, high-dimensional data due to high training and inference costs. In this work, we introduce a Plug-and-play algorithm for 3D stochastic inference with latent diffusion prior (PSI3D) to address massive ($1024\\times 1024\\times 128$) volumes. Specifically, we formulate a Markov chain Monte Carlo approach to reconstruct each two-dimensional (2D) slice by sampling from a 2D latent diffusion model. To enhance inter-slice consistency, we also incorporate tota"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.18367","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/2512.18367/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":"2512.18367","created_at":"2026-08-06T01:16:47.395729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.18367v2","created_at":"2026-08-06T01:16:47.395729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.18367","created_at":"2026-08-06T01:16:47.395729+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKBGOH4ZAC7U","created_at":"2026-08-06T01:16:47.395729+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKBGOH4ZAC7UXIE7","created_at":"2026-08-06T01:16:47.395729+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKBGOH4Z","created_at":"2026-08-06T01:16:47.395729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE","json":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE.json","graph_json":"https://pith.science/api/pith-number/NKBGOH4ZAC7UXIE7GNUXWPBYCE/graph.json","events_json":"https://pith.science/api/pith-number/NKBGOH4ZAC7UXIE7GNUXWPBYCE/events.json","paper":"https://pith.science/paper/NKBGOH4Z"},"agent_actions":{"view_html":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE","download_json":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE.json","view_paper":"https://pith.science/paper/NKBGOH4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.18367&json=true","fetch_graph":"https://pith.science/api/pith-number/NKBGOH4ZAC7UXIE7GNUXWPBYCE/graph.json","fetch_events":"https://pith.science/api/pith-number/NKBGOH4ZAC7UXIE7GNUXWPBYCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE/action/storage_attestation","attest_author":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE/action/author_attestation","sign_citation":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE/action/citation_signature","submit_replication":"https://pith.science/pith/NKBGOH4ZAC7UXIE7GNUXWPBYCE/action/replication_record"}},"created_at":"2026-08-06T01:16:47.395729+00:00","updated_at":"2026-08-06T01:16:47.395729+00:00"}