{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ORHJJHQL7BDI24P3KMSRG4YR6F","short_pith_number":"pith:ORHJJHQL","schema_version":"1.0","canonical_sha256":"744e949e0bf8468d71fb5325137311f165a3b63a285cb008751ebf16e0bf2c92","source":{"kind":"arxiv","id":"2608.05844","version":1},"attestation_state":"computed","paper":{"title":"Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Saporta, Corentin Dancette, L\\'eo Alberge, Th\\'eo Danielou","submitted_at":"2026-08-06T10:17:23Z","abstract_excerpt":"Radiology foundation models learn transferable representations that can be adapted to new tasks by training only small layers on top of a frozen encoder. Dense prediction tasks such as 3D segmentation are, however, underrepresented in their evaluation, and, with the encoder kept frozen, pre-trained models still fall short of nnU-Net, the state-of-the-art reference trained from scratch. To close this gap we extend convolutional MAE pre-training with a robust reconstruction objective, a feature regularizer, and a local-global similarity objective. Using this method, we propose Curia-MAE, a multi"},"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":"2608.05844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T10:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"4064baca91809f520a4c3fb2c9866fc18308c29cd5d428ff51f33fd340f88c42","abstract_canon_sha256":"6b6717b9c96e15f1167dc0dec65400af4565c493755a9d43edda5728c8cdb0b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:52.456484Z","signature_b64":"S0jaL2yAN4UTsRPRPumVSugFysPmh6QGTt0URqHw9Bxs1oy4yTjy5V5ZQUqU4SsCvevHRjyNYyHuq24ayoYKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"744e949e0bf8468d71fb5325137311f165a3b63a285cb008751ebf16e0bf2c92","last_reissued_at":"2026-08-07T00:52:52.455076Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:52.455076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Saporta, Corentin Dancette, L\\'eo Alberge, Th\\'eo Danielou","submitted_at":"2026-08-06T10:17:23Z","abstract_excerpt":"Radiology foundation models learn transferable representations that can be adapted to new tasks by training only small layers on top of a frozen encoder. Dense prediction tasks such as 3D segmentation are, however, underrepresented in their evaluation, and, with the encoder kept frozen, pre-trained models still fall short of nnU-Net, the state-of-the-art reference trained from scratch. To close this gap we extend convolutional MAE pre-training with a robust reconstruction objective, a feature regularizer, and a local-global similarity objective. Using this method, we propose Curia-MAE, a multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05844","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/2608.05844/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":"2608.05844","created_at":"2026-08-07T00:52:52.456574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05844v1","created_at":"2026-08-07T00:52:52.456574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05844","created_at":"2026-08-07T00:52:52.456574+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORHJJHQL7BDI","created_at":"2026-08-07T00:52:52.456574+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORHJJHQL7BDI24P3","created_at":"2026-08-07T00:52:52.456574+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORHJJHQL","created_at":"2026-08-07T00:52:52.456574+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/ORHJJHQL7BDI24P3KMSRG4YR6F","json":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F.json","graph_json":"https://pith.science/api/pith-number/ORHJJHQL7BDI24P3KMSRG4YR6F/graph.json","events_json":"https://pith.science/api/pith-number/ORHJJHQL7BDI24P3KMSRG4YR6F/events.json","paper":"https://pith.science/paper/ORHJJHQL"},"agent_actions":{"view_html":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F","download_json":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F.json","view_paper":"https://pith.science/paper/ORHJJHQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05844&json=true","fetch_graph":"https://pith.science/api/pith-number/ORHJJHQL7BDI24P3KMSRG4YR6F/graph.json","fetch_events":"https://pith.science/api/pith-number/ORHJJHQL7BDI24P3KMSRG4YR6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F/action/storage_attestation","attest_author":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F/action/author_attestation","sign_citation":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F/action/citation_signature","submit_replication":"https://pith.science/pith/ORHJJHQL7BDI24P3KMSRG4YR6F/action/replication_record"}},"created_at":"2026-08-07T00:52:52.456574+00:00","updated_at":"2026-08-07T00:52:52.456574+00:00"}