{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TISNWF2TUV75V5KNFBIJSCEZNX","short_pith_number":"pith:TISNWF2T","schema_version":"1.0","canonical_sha256":"9a24db1753a57fdaf54d28509908996de7a7bc0577d75eababe69420721fd48f","source":{"kind":"arxiv","id":"2608.06613","version":1},"attestation_state":"computed","paper":{"title":"Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniel Klaaby, Julia Anna Mielcarz, Mostafa Mehdipour Ghazi","submitted_at":"2026-08-06T21:55:41Z","abstract_excerpt":"Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remains poorly understood. We present a controlled evaluation of representation robustness across five pretrained 3D encoders spanning different architectures, objectives, pretraining domains, and dataset scales. Using BraTS-Africa cases with four MRI sequences, we generate seven frequency- and image-domain artifacts at five predefined corruption settings. Robustness is assessed using linear centered kernel alignment (CKA), RankMe, and UMAP, complemen"},"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":"2608.06613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T21:55:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0499a292a9c4816b2544ae9590686650593fe0fe831431623d245f65e153fa22","abstract_canon_sha256":"b3a79c666da6848d26742a5cc329345963f325ba2768937e9a3294a3655ee21c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:11:29.085446Z","signature_b64":"SL8dWNNR/rFVAx64nLnmLo+y6naXMozU4NqvcBgsSAfTsgLhOcEX9p/96EOxB5RSSMtF22gQVYUaBJRlVDqGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a24db1753a57fdaf54d28509908996de7a7bc0577d75eababe69420721fd48f","last_reissued_at":"2026-08-10T01:11:29.082570Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:11:29.082570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniel Klaaby, Julia Anna Mielcarz, Mostafa Mehdipour Ghazi","submitted_at":"2026-08-06T21:55:41Z","abstract_excerpt":"Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remains poorly understood. We present a controlled evaluation of representation robustness across five pretrained 3D encoders spanning different architectures, objectives, pretraining domains, and dataset scales. Using BraTS-Africa cases with four MRI sequences, we generate seven frequency- and image-domain artifacts at five predefined corruption settings. Robustness is assessed using linear centered kernel alignment (CKA), RankMe, and UMAP, complemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06613","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/2608.06613/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":"2608.06613","created_at":"2026-08-10T01:11:29.083959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06613v1","created_at":"2026-08-10T01:11:29.083959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06613","created_at":"2026-08-10T01:11:29.083959+00:00"},{"alias_kind":"pith_short_12","alias_value":"TISNWF2TUV75","created_at":"2026-08-10T01:11:29.083959+00:00"},{"alias_kind":"pith_short_16","alias_value":"TISNWF2TUV75V5KN","created_at":"2026-08-10T01:11:29.083959+00:00"},{"alias_kind":"pith_short_8","alias_value":"TISNWF2T","created_at":"2026-08-10T01:11:29.083959+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/TISNWF2TUV75V5KNFBIJSCEZNX","json":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX.json","graph_json":"https://pith.science/api/pith-number/TISNWF2TUV75V5KNFBIJSCEZNX/graph.json","events_json":"https://pith.science/api/pith-number/TISNWF2TUV75V5KNFBIJSCEZNX/events.json","paper":"https://pith.science/paper/TISNWF2T"},"agent_actions":{"view_html":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX","download_json":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX.json","view_paper":"https://pith.science/paper/TISNWF2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06613&json=true","fetch_graph":"https://pith.science/api/pith-number/TISNWF2TUV75V5KNFBIJSCEZNX/graph.json","fetch_events":"https://pith.science/api/pith-number/TISNWF2TUV75V5KNFBIJSCEZNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX/action/storage_attestation","attest_author":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX/action/author_attestation","sign_citation":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX/action/citation_signature","submit_replication":"https://pith.science/pith/TISNWF2TUV75V5KNFBIJSCEZNX/action/replication_record"}},"created_at":"2026-08-10T01:11:29.083959+00:00","updated_at":"2026-08-10T01:11:29.083959+00:00"}