{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DOFG4SYQUZ23DSXPSRO7SPBUSI","short_pith_number":"pith:DOFG4SYQ","schema_version":"1.0","canonical_sha256":"1b8a6e4b10a675b1caef945df93c3492165d7221c23369d5c2f22b7ded814648","source":{"kind":"arxiv","id":"2606.08164","version":1},"attestation_state":"computed","paper":{"title":"How Much MRI Preprocessing Is Enough? A Cost-Utility Study for Brain MRI Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangshuan Pang, Jing Yan, Shiping Liu, Tao Zhou, Wangyang Tang, Youzhe He, Zhenkun Zhuang, Zhixuan Cheng","submitted_at":"2026-06-06T13:26:01Z","abstract_excerpt":"MRI preprocessing defines the input distribution seen by brain MRI foundation models, yet it is usually treated as routine data cleaning rather than a modeling choice. We ask how much preprocessing is worth its computational cost for self-supervised 3D MRI pretraining. Keeping the corpus, 3D ViT backbone, masking protocol, and downstream evaluations fixed, we compare a graded P0-P7 preprocessing spectrum for masked autoencoding (MAE) and joint-embedding predictive learning (JEPA) on 20,000 heterogeneous brain MRI volumes, then transfer the encoders to IDH prediction, MCI classification, brain "},"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":"2606.08164","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T13:26:01Z","cross_cats_sorted":[],"title_canon_sha256":"de7f913e5e7399dc24bc5401928c91e540ce7ad1543bd4693fd0c6c30fc85aaa","abstract_canon_sha256":"7148ce153353c85f42b82866576515af44b244ab5dba8c165cae1cd5a12d48f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:28.725230Z","signature_b64":"63JGYF0aLwSnQCVW3x1EeIGOFxXlGsl3O0Yq0A8oifgItu7WWy52vi2xdY8aUgnE9S9mqayB6UjWfJpI1zgPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b8a6e4b10a675b1caef945df93c3492165d7221c23369d5c2f22b7ded814648","last_reissued_at":"2026-06-09T01:05:28.724577Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:28.724577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Much MRI Preprocessing Is Enough? A Cost-Utility Study for Brain MRI Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangshuan Pang, Jing Yan, Shiping Liu, Tao Zhou, Wangyang Tang, Youzhe He, Zhenkun Zhuang, Zhixuan Cheng","submitted_at":"2026-06-06T13:26:01Z","abstract_excerpt":"MRI preprocessing defines the input distribution seen by brain MRI foundation models, yet it is usually treated as routine data cleaning rather than a modeling choice. We ask how much preprocessing is worth its computational cost for self-supervised 3D MRI pretraining. Keeping the corpus, 3D ViT backbone, masking protocol, and downstream evaluations fixed, we compare a graded P0-P7 preprocessing spectrum for masked autoencoding (MAE) and joint-embedding predictive learning (JEPA) on 20,000 heterogeneous brain MRI volumes, then transfer the encoders to IDH prediction, MCI classification, brain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08164","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/2606.08164/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":"2606.08164","created_at":"2026-06-09T01:05:28.724680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08164v1","created_at":"2026-06-09T01:05:28.724680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08164","created_at":"2026-06-09T01:05:28.724680+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOFG4SYQUZ23","created_at":"2026-06-09T01:05:28.724680+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOFG4SYQUZ23DSXP","created_at":"2026-06-09T01:05:28.724680+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOFG4SYQ","created_at":"2026-06-09T01:05:28.724680+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/DOFG4SYQUZ23DSXPSRO7SPBUSI","json":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI.json","graph_json":"https://pith.science/api/pith-number/DOFG4SYQUZ23DSXPSRO7SPBUSI/graph.json","events_json":"https://pith.science/api/pith-number/DOFG4SYQUZ23DSXPSRO7SPBUSI/events.json","paper":"https://pith.science/paper/DOFG4SYQ"},"agent_actions":{"view_html":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI","download_json":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI.json","view_paper":"https://pith.science/paper/DOFG4SYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08164&json=true","fetch_graph":"https://pith.science/api/pith-number/DOFG4SYQUZ23DSXPSRO7SPBUSI/graph.json","fetch_events":"https://pith.science/api/pith-number/DOFG4SYQUZ23DSXPSRO7SPBUSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI/action/storage_attestation","attest_author":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI/action/author_attestation","sign_citation":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI/action/citation_signature","submit_replication":"https://pith.science/pith/DOFG4SYQUZ23DSXPSRO7SPBUSI/action/replication_record"}},"created_at":"2026-06-09T01:05:28.724680+00:00","updated_at":"2026-06-09T01:05:28.724680+00:00"}