{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBE6VWX6ECDWRLXK4CTUVQPI75","short_pith_number":"pith:BBE6VWX6","schema_version":"1.0","canonical_sha256":"0849eadafe208768aeeae0a74ac1e8ff79748b5f7af8ccb194ca471e71540c94","source":{"kind":"arxiv","id":"2503.00266","version":1},"attestation_state":"computed","paper":{"title":"Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dena Shahriari, Ilker Hacihaliloglu, Milad Yazdani, Pooria Ashrafian, Yasamin Medghalchi","submitted_at":"2025-03-01T00:49:47Z","abstract_excerpt":"Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative models, such as diffusion models, offer a potential solution by synthesizing medical images, but their practical adoption is hindered by long inference times. In this paper, we propose the use of an optimal transport flow matching approach to accelerate image generation. By introducing a straighter mapping between the source and target distribution, our metho"},"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":"2503.00266","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-01T00:49:47Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"e45dd5d1fade13548f9cd8861f0c8c34379da42dc918e66227657775732002f5","abstract_canon_sha256":"79206c7e0bb01dc39d883ed8a58bfc3d0b840ddf9671b010ecd74f6e912cb732"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:19.811719Z","signature_b64":"KMr7qBE65WrXM00jSXzVFIS5WTPpRgVBnAKA9khACHFV6efXQyWPqAdOXLSuEKsTdOgwBkhzCkPqTKhF3gnoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0849eadafe208768aeeae0a74ac1e8ff79748b5f7af8ccb194ca471e71540c94","last_reissued_at":"2026-07-05T10:22:19.811240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:19.811240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dena Shahriari, Ilker Hacihaliloglu, Milad Yazdani, Pooria Ashrafian, Yasamin Medghalchi","submitted_at":"2025-03-01T00:49:47Z","abstract_excerpt":"Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative models, such as diffusion models, offer a potential solution by synthesizing medical images, but their practical adoption is hindered by long inference times. In this paper, we propose the use of an optimal transport flow matching approach to accelerate image generation. By introducing a straighter mapping between the source and target distribution, our metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00266","kind":"arxiv","version":1},"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/2503.00266/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":"2503.00266","created_at":"2026-07-05T10:22:19.811302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00266v1","created_at":"2026-07-05T10:22:19.811302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00266","created_at":"2026-07-05T10:22:19.811302+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBE6VWX6ECDW","created_at":"2026-07-05T10:22:19.811302+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBE6VWX6ECDWRLXK","created_at":"2026-07-05T10:22:19.811302+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBE6VWX6","created_at":"2026-07-05T10:22:19.811302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08670","citing_title":"WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75","json":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75.json","graph_json":"https://pith.science/api/pith-number/BBE6VWX6ECDWRLXK4CTUVQPI75/graph.json","events_json":"https://pith.science/api/pith-number/BBE6VWX6ECDWRLXK4CTUVQPI75/events.json","paper":"https://pith.science/paper/BBE6VWX6"},"agent_actions":{"view_html":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75","download_json":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75.json","view_paper":"https://pith.science/paper/BBE6VWX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00266&json=true","fetch_graph":"https://pith.science/api/pith-number/BBE6VWX6ECDWRLXK4CTUVQPI75/graph.json","fetch_events":"https://pith.science/api/pith-number/BBE6VWX6ECDWRLXK4CTUVQPI75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75/action/storage_attestation","attest_author":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75/action/author_attestation","sign_citation":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75/action/citation_signature","submit_replication":"https://pith.science/pith/BBE6VWX6ECDWRLXK4CTUVQPI75/action/replication_record"}},"created_at":"2026-07-05T10:22:19.811302+00:00","updated_at":"2026-07-05T10:22:19.811302+00:00"}