{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YUXUQNFI4ZTTPXM22QT35OF4DP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e0bc428d4b8850def47bccafc0112c2e2ee01e4bce4141ed6ff20cd2fba5d370","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:05:15Z","title_canon_sha256":"8d52f725c9dc02e657ac6bcbc0f31d46273c841520ac15935d6c94234808dfad"},"schema_version":"1.0","source":{"id":"2605.16469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16469","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16469v1","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16469","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"YUXUQNFI4ZTT","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"YUXUQNFI4ZTTPXM2","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"YUXUQNFI","created_at":"2026-05-20T00:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:1147ac78f1023d47ced30f58c85768eff28f7a0d13c68ab6f5151d30133ba446","target":"graph","created_at":"2026-05-20T00:02:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On long-tailed chest X-ray (MIMIC-LT, NIH-LT) and CT slice (CT-RATE) benchmarks the proposed method consistently improves tail-class generation fidelity and diversity (FID, IRS) and is a promising augmentation strategy that reliably improves downstream balanced accuracy and macro-F1 over a non-augmented baseline across modalities."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That partitioning coarse labels into coherent submodes via Gaussian mixture modeling in the generative model's latent space will yield useful subclasses, and that learning subclass-conditioned source distributions will shorten transport paths and reduce dispersion without introducing new biases or degeneracies that the geometric control cannot fully mitigate."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Optimizes subclass priors in flow matching via latent GMM partitioning and conditioned sources to improve rare disease image generation fidelity, diversity, and downstream classification on long-tailed medical datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Partitioning coarse labels into latent submodes and learning subclass-conditioned sources lets flow matching generate more faithful rare medical images while improving downstream classifier accuracy."}],"snapshot_sha256":"9af2b53965e2129b205e1336b16bf36128daf8b61a46ac5f8630155130334c7c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:01:30.290042Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.286285Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:23.118207Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.055136Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16469/integrity.json","findings":[],"snapshot_sha256":"09fff9d5a5ced1d9d751b9ebcd470d6a0c588bac852ecab35d9b214e92e1a817","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rare diseases dominate the diagnostic challenge in medical imaging yet are severely underrepresented in clinical datasets, causing classifiers to fail on exactly the conditions where reliable detection matters most. Generative augmentation can supply the missing tail-class coverage, but coarse disease labels aggregate diverse subtypes and acquisition settings into multi-modal conditionals that bias generators toward dominant submodes, while a shared Gaussian source forces rare subpopulations through disproportionately long transport paths. We propose an offline strategy that introduces informa","authors_text":"Bernhard Kainz, Felix N\\\"utzel, Mischa Dombrowski","cross_cats":["cs.CV"],"headline":"Partitioning coarse labels into latent submodes and learning subclass-conditioned sources lets flow matching generate more faithful rare medical images while improving downstream classifier accuracy.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:05:15Z","title":"Flow Matching with Optimized Subclass Priors for Medical Image Augmentation"},"references":{"count":35,"internal_anchors":0,"resolved_work":35,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Adaloglou, N., Kaiser, T., Michels, F., Kollmann, M.: Rethinking cluster- conditioned diffusion models for label-free image synthesis. In: WACV’25. pp. 3603–3613. IEEE (2025)","work_id":"51b491db-7ac7-4aff-a933-3844e0810660","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Bao, F., Li, C., Sun, J., Zhu, J.: Why are conditional generative models better than unconditional ones? In: NeurIPS’22 Workshop on Score-Based Methods (2022)","work_id":"fc45ed12-c1d1-4ffc-bb00-97b82b1190d0","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Boecking, B., Usuyama, N., Bannur, S., Castro, D.C., Schwaighofer, A., Hyland, S., Wetscherek, M., Naumann, T., Nori, A., Alvarez-Valle, J., Poon, H., Oktay, O.: Making the most of text semantics to i","work_id":"57f499a6-9ed8-4063-8029-ef9eb7dfd1cc","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"In: MICCAI’25","work_id":"22717960-d391-42dc-9cb7-3819bf8ceb2d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In: BRIDGE/DeCaF @ MICCAI’25","work_id":"1e7149e9-ac44-4510-9fdc-6d97f2ffcea1","year":2026}],"snapshot_sha256":"3d3fccea660ff660bf6d705ba6a470699fe0740f94b26343ee209f2fc0a662b4"},"source":{"id":"2605.16469","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:48:41.811518Z","id":"3281fe93-6b57-49f6-9c8b-e7098587b53a","model_set":{"reader":"grok-4.3"},"one_line_summary":"Optimizes subclass priors in flow matching via latent GMM partitioning and conditioned sources to improve rare disease image generation fidelity, diversity, and downstream classification on long-tailed medical datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Partitioning coarse labels into latent submodes and learning subclass-conditioned sources lets flow matching generate more faithful rare medical images while improving downstream classifier accuracy.","strongest_claim":"On long-tailed chest X-ray (MIMIC-LT, NIH-LT) and CT slice (CT-RATE) benchmarks the proposed method consistently improves tail-class generation fidelity and diversity (FID, IRS) and is a promising augmentation strategy that reliably improves downstream balanced accuracy and macro-F1 over a non-augmented baseline across modalities.","weakest_assumption":"That partitioning coarse labels into coherent submodes via Gaussian mixture modeling in the generative model's latent space will yield useful subclasses, and that learning subclass-conditioned source distributions will shorten transport paths and reduce dispersion without introducing new biases or degeneracies that the geometric control cannot fully mitigate."}},"verdict_id":"3281fe93-6b57-49f6-9c8b-e7098587b53a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:38a9b4378e8e837b3dd489e9cac3f3075a2a69be0bd6284f1eaa4908ed556504","target":"record","created_at":"2026-05-20T00:02:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e0bc428d4b8850def47bccafc0112c2e2ee01e4bce4141ed6ff20cd2fba5d370","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:05:15Z","title_canon_sha256":"8d52f725c9dc02e657ac6bcbc0f31d46273c841520ac15935d6c94234808dfad"},"schema_version":"1.0","source":{"id":"2605.16469","kind":"arxiv","version":1}},"canonical_sha256":"c52f4834a8e66737dd9ad427beb8bc1bc18be41456ede053a42489a67d31d9bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c52f4834a8e66737dd9ad427beb8bc1bc18be41456ede053a42489a67d31d9bc","first_computed_at":"2026-05-20T00:02:23.576283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:23.576283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A8IuR/Kz1QQuRrqGslZLsAvPWUmVfyVaS0l+8hQw4bEI7wh4eGi92jThqZuJfP7kQ8LumZweBDiRyl5gvKclDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:23.577173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38a9b4378e8e837b3dd489e9cac3f3075a2a69be0bd6284f1eaa4908ed556504","sha256:1147ac78f1023d47ced30f58c85768eff28f7a0d13c68ab6f5151d30133ba446"],"state_sha256":"967ad2f3981bc9c0c7146c829a34c2ffa4c56880706c9d92eda043e420012cdb"}