{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FXTNBVHTTYAZV36SWBLF6RYMQR","short_pith_number":"pith:FXTNBVHT","schema_version":"1.0","canonical_sha256":"2de6d0d4f39e019aefd2b0565f470c847f0038b2bb92731e585976a9fedad018","source":{"kind":"arxiv","id":"2212.08034","version":2},"attestation_state":"computed","paper":{"title":"Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Ehsan Adeli, Kilian M. Pohl, Qingyu Zhao, Sang Hyun Park, Tomas Bosschieter, Wei Peng","submitted_at":"2022-12-15T18:45:13Z","abstract_excerpt":"As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models. This challenge could be reduced by MRI synthesis, for which Generative Adversarial Networks (GANs) are popular. GANs, however, are commonly unstable and struggle with creating diverse and high-quality data. A more stable alternative is Diffusion Probabilistic Models (DPMs) with a fine-grained training strategy. To overcome their need for extensive computational resources, we propose a conditional DPM (cDPM) with a memory-efficient process that generate"},"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":"2212.08034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2022-12-15T18:45:13Z","cross_cats_sorted":[],"title_canon_sha256":"99cd38998fbf7aff2ed7a5daff0a25137d6504aa3906f29c2678173ef017278b","abstract_canon_sha256":"b7a0208d8608f9f78b08793f877521d6825c26e8bdd01022d438b75c08901800"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:32.744762Z","signature_b64":"ghkB9Vcl/juOp0Ux1t3PnNKNL5ihyCOdGWEhQ6BzhRqloC2EXjO60Li3xv7G4I6psxcd9KuuxY8OhwIihyohBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2de6d0d4f39e019aefd2b0565f470c847f0038b2bb92731e585976a9fedad018","last_reissued_at":"2026-07-05T06:48:32.744214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:32.744214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Ehsan Adeli, Kilian M. Pohl, Qingyu Zhao, Sang Hyun Park, Tomas Bosschieter, Wei Peng","submitted_at":"2022-12-15T18:45:13Z","abstract_excerpt":"As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models. This challenge could be reduced by MRI synthesis, for which Generative Adversarial Networks (GANs) are popular. GANs, however, are commonly unstable and struggle with creating diverse and high-quality data. A more stable alternative is Diffusion Probabilistic Models (DPMs) with a fine-grained training strategy. To overcome their need for extensive computational resources, we propose a conditional DPM (cDPM) with a memory-efficient process that generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08034","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/2212.08034/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":"2212.08034","created_at":"2026-07-05T06:48:32.744273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08034v2","created_at":"2026-07-05T06:48:32.744273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08034","created_at":"2026-07-05T06:48:32.744273+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXTNBVHTTYAZ","created_at":"2026-07-05T06:48:32.744273+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXTNBVHTTYAZV36S","created_at":"2026-07-05T06:48:32.744273+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXTNBVHT","created_at":"2026-07-05T06:48:32.744273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01185","citing_title":"Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR","json":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR.json","graph_json":"https://pith.science/api/pith-number/FXTNBVHTTYAZV36SWBLF6RYMQR/graph.json","events_json":"https://pith.science/api/pith-number/FXTNBVHTTYAZV36SWBLF6RYMQR/events.json","paper":"https://pith.science/paper/FXTNBVHT"},"agent_actions":{"view_html":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR","download_json":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR.json","view_paper":"https://pith.science/paper/FXTNBVHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08034&json=true","fetch_graph":"https://pith.science/api/pith-number/FXTNBVHTTYAZV36SWBLF6RYMQR/graph.json","fetch_events":"https://pith.science/api/pith-number/FXTNBVHTTYAZV36SWBLF6RYMQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR/action/storage_attestation","attest_author":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR/action/author_attestation","sign_citation":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR/action/citation_signature","submit_replication":"https://pith.science/pith/FXTNBVHTTYAZV36SWBLF6RYMQR/action/replication_record"}},"created_at":"2026-07-05T06:48:32.744273+00:00","updated_at":"2026-07-05T06:48:32.744273+00:00"}