{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D26KXACXHSYJCRXKIQJ3HJABSZ","short_pith_number":"pith:D26KXACX","schema_version":"1.0","canonical_sha256":"1ebcab80573cb09146ea4413b3a401965239080ca7950ce7d4a442b82bec6522","source":{"kind":"arxiv","id":"2607.13300","version":1},"attestation_state":"computed","paper":{"title":"Improving Medical Image Generative Models with Fr\\'echet Distance Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Marshall, James Duncan, Lawrence Staib, Rui Wang, Xiaoran Zhang, Xuanang Xu","submitted_at":"2026-07-14T22:11:15Z","abstract_excerpt":"Diffusion generative models have demonstrated immense potential for synthetic medical image generation. However, these models often struggle to capture complex morphological characteristics of heterogeneous tumors with irregular boundaries, limiting their utility for downstream clinical tasks such as segmentation. This limitation stems from the standard denoising objective: minimizing a per-pixel error, which smooths high-variance irregular structures characteristic of tumors. To address this, we propose finetuning these generative models with Fr\\'echet Distance loss (FD-loss). FD-loss aligns "},"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":"2607.13300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T22:11:15Z","cross_cats_sorted":[],"title_canon_sha256":"1da6fd98d3b48611292069d83070179d6d889cd37763b15c9cfce2fb643829b9","abstract_canon_sha256":"62018d62a6ad92b06ba0dd9b77e64c4be2c8429108960d8dc97944a4a9f77cc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:08.456331Z","signature_b64":"8K9f0GQZq9zEiBli19RppzTqtQl2PDmDuyP59jir0NLCED/gQ9TB1mvqtzkdQ5Z4mjMiSYkpadDlH8Y+QJjPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ebcab80573cb09146ea4413b3a401965239080ca7950ce7d4a442b82bec6522","last_reissued_at":"2026-07-16T00:22:08.455584Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:08.455584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Medical Image Generative Models with Fr\\'echet Distance Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Marshall, James Duncan, Lawrence Staib, Rui Wang, Xiaoran Zhang, Xuanang Xu","submitted_at":"2026-07-14T22:11:15Z","abstract_excerpt":"Diffusion generative models have demonstrated immense potential for synthetic medical image generation. However, these models often struggle to capture complex morphological characteristics of heterogeneous tumors with irregular boundaries, limiting their utility for downstream clinical tasks such as segmentation. This limitation stems from the standard denoising objective: minimizing a per-pixel error, which smooths high-variance irregular structures characteristic of tumors. To address this, we propose finetuning these generative models with Fr\\'echet Distance loss (FD-loss). FD-loss aligns "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13300","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/2607.13300/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":"2607.13300","created_at":"2026-07-16T00:22:08.455990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13300v1","created_at":"2026-07-16T00:22:08.455990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13300","created_at":"2026-07-16T00:22:08.455990+00:00"},{"alias_kind":"pith_short_12","alias_value":"D26KXACXHSYJ","created_at":"2026-07-16T00:22:08.455990+00:00"},{"alias_kind":"pith_short_16","alias_value":"D26KXACXHSYJCRXK","created_at":"2026-07-16T00:22:08.455990+00:00"},{"alias_kind":"pith_short_8","alias_value":"D26KXACX","created_at":"2026-07-16T00:22:08.455990+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/D26KXACXHSYJCRXKIQJ3HJABSZ","json":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ.json","graph_json":"https://pith.science/api/pith-number/D26KXACXHSYJCRXKIQJ3HJABSZ/graph.json","events_json":"https://pith.science/api/pith-number/D26KXACXHSYJCRXKIQJ3HJABSZ/events.json","paper":"https://pith.science/paper/D26KXACX"},"agent_actions":{"view_html":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ","download_json":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ.json","view_paper":"https://pith.science/paper/D26KXACX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13300&json=true","fetch_graph":"https://pith.science/api/pith-number/D26KXACXHSYJCRXKIQJ3HJABSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/D26KXACXHSYJCRXKIQJ3HJABSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ/action/storage_attestation","attest_author":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ/action/author_attestation","sign_citation":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ/action/citation_signature","submit_replication":"https://pith.science/pith/D26KXACXHSYJCRXKIQJ3HJABSZ/action/replication_record"}},"created_at":"2026-07-16T00:22:08.455990+00:00","updated_at":"2026-07-16T00:22:08.455990+00:00"}