{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QIWCR4VNM3DSZRVAZZJA3YVGZQ","short_pith_number":"pith:QIWCR4VN","schema_version":"1.0","canonical_sha256":"822c28f2ad66c72cc6a0ce520de2a6cc2bba8065d337f170e855ef50ed0ccc68","source":{"kind":"arxiv","id":"2605.10629","version":1},"attestation_state":"computed","paper":{"title":"Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A compact product-of-Gaussian-mixture diffusion model acts as an image prior for joint reconstruction of MRI images and coil sensitivities.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Laurenz Nagler, Martin Zach, Thomas Pock","submitted_at":"2026-05-11T14:20:30Z","abstract_excerpt":"Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-conditioning mechanisms, and require offline coil sensitivity estimation. This results in limited interpretability of the reconstruction process and reduced flexibility in the acquisition setup. To address these limitations, we jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior wi"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.10629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T14:20:30Z","cross_cats_sorted":[],"title_canon_sha256":"b51cf58296a9e5f43ab27a184910cf425dc2a5b8d26cc4b4be1eb67dee8e8734","abstract_canon_sha256":"9c6bef00da3e3cb93aaa644d00e4a8b2a85e6176bb1b6f7e3fdcd7558c16b7a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:22.695807Z","signature_b64":"cguzLa/hqwa2TzbDk6QZdZAewdTMI7gKuG6cC7gCLlPA+14V+fc/mYB7ALcEAulWVcLCwUas6XGQP99y/3rDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"822c28f2ad66c72cc6a0ce520de2a6cc2bba8065d337f170e855ef50ed0ccc68","last_reissued_at":"2026-06-30T02:17:22.695263Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:22.695263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A compact product-of-Gaussian-mixture diffusion model acts as an image prior for joint reconstruction of MRI images and coil sensitivities.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Laurenz Nagler, Martin Zach, Thomas Pock","submitted_at":"2026-05-11T14:20:30Z","abstract_excerpt":"Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-conditioning mechanisms, and require offline coil sensitivity estimation. This results in limited interpretability of the reconstruction process and reduced flexibility in the acquisition setup. To address these limitations, we jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior wi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior with a classical smoothness prior on the coil sensitivities. The proposed method is fast and robust to both contrast and anatomical distribution shifts as well as changing k-space trajectories. Finally, we propose a more expressive parameterization of the image prior which improves results in denoising and magnetic resonance image reconstruction.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the product-of-Gaussian-mixture diffusion model provides a sufficiently general and effective prior for MRI images across varying contrasts and anatomies, and that a classical smoothness prior is adequate to model coil sensitivities without introducing reconstruction artifacts or requiring additional constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A joint MRI reconstruction method using product-of-Gaussian-mixture diffusion models for the image prior and smoothness priors for coil sensitivities, with an improved parameterization for better denoising and reconstruction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A compact product-of-Gaussian-mixture diffusion model acts as an image prior for joint reconstruction of MRI images and coil sensitivities.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"98e02dbb3af345f6bf25c2bde980bd1245d858da2e657f7158ee0b2b81bc39d2"},"source":{"id":"2605.10629","kind":"arxiv","version":1},"verdict":{"id":"4afd6bf1-67c7-40a7-aea8-08d0492cd5be","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T05:12:17.888827Z","strongest_claim":"We jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior with a classical smoothness prior on the coil sensitivities. The proposed method is fast and robust to both contrast and anatomical distribution shifts as well as changing k-space trajectories. Finally, we propose a more expressive parameterization of the image prior which improves results in denoising and magnetic resonance image reconstruction.","one_line_summary":"A joint MRI reconstruction method using product-of-Gaussian-mixture diffusion models for the image prior and smoothness priors for coil sensitivities, with an improved parameterization for better denoising and reconstruction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the product-of-Gaussian-mixture diffusion model provides a sufficiently general and effective prior for MRI images across varying contrasts and anatomies, and that a classical smoothness prior is adequate to model coil sensitivities without introducing reconstruction artifacts or requiring additional constraints.","pith_extraction_headline":"A compact product-of-Gaussian-mixture diffusion model acts as an image prior for joint reconstruction of MRI images and coil sensitivities."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10629/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:42:00.768851Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:40:15.399410Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:17.436081Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:05:12.945759Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b6c91961bab3550f15c0bb5bdd2967390c281485897124849b610d1ae738d236"},"references":{"count":79,"sample":[{"doi":"","year":1999,"title":"Magnetic Resonance in Medicine42(5), 952–962 (1999)","work_id":"6fc6b418-22f6-4cab-82bb-c2a685d49201","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"Magnetic Resonance in Medicine47(6), 1202–1210 (2002)","work_id":"1aa6ce94-a288-4730-abc1-aacc4117aa5b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2007,"title":"iterative image reconstruction using a total variation constraint","work_id":"a4bcf2ad-548f-4580-a41b-28ac82c011f1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Magnetic Resonance in Medicine65(2), 480–491 (2011)","work_id":"89217db2-37fe-478d-9f86-f432326e5b39","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Magnetic Resonance in Medicine79(6), 3055–3071 (2018)","work_id":"5cf24b4b-861a-4c72-a868-9f7720df796c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":79,"snapshot_sha256":"8a5aa2426763848e19b915769a3a4e391bbe653260214d71329a98eb9a9c219c","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ac8cd57a7b54bb3df033d88ddfb04d9fd1ef40ebbc4b9032b835857808512150"},"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":"2605.10629","created_at":"2026-06-30T02:17:22.695349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10629v1","created_at":"2026-06-30T02:17:22.695349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10629","created_at":"2026-06-30T02:17:22.695349+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIWCR4VNM3DS","created_at":"2026-06-30T02:17:22.695349+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIWCR4VNM3DSZRVA","created_at":"2026-06-30T02:17:22.695349+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIWCR4VN","created_at":"2026-06-30T02:17:22.695349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ","json":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ.json","graph_json":"https://pith.science/api/pith-number/QIWCR4VNM3DSZRVAZZJA3YVGZQ/graph.json","events_json":"https://pith.science/api/pith-number/QIWCR4VNM3DSZRVAZZJA3YVGZQ/events.json","paper":"https://pith.science/paper/QIWCR4VN"},"agent_actions":{"view_html":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ","download_json":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ.json","view_paper":"https://pith.science/paper/QIWCR4VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10629&json=true","fetch_graph":"https://pith.science/api/pith-number/QIWCR4VNM3DSZRVAZZJA3YVGZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QIWCR4VNM3DSZRVAZZJA3YVGZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ/action/storage_attestation","attest_author":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ/action/author_attestation","sign_citation":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ/action/citation_signature","submit_replication":"https://pith.science/pith/QIWCR4VNM3DSZRVAZZJA3YVGZQ/action/replication_record"}},"created_at":"2026-06-30T02:17:22.695349+00:00","updated_at":"2026-06-30T02:17:22.695349+00:00"}