{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LXI5WCQM535D6JLZ25UEFDX2T7","short_pith_number":"pith:LXI5WCQM","schema_version":"1.0","canonical_sha256":"5dd1db0a0ceefa3f2579d768428efa9fd88b27d66db11e8c278bdfd9d7387e0c","source":{"kind":"arxiv","id":"2606.14957","version":2},"attestation_state":"computed","paper":{"title":"Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Masurkar, Daniel Orringer, Haoxu Huang, James Ryan Loftus, Jennifer Frontera, Jingyun Chen, Jinu Hyun, Kara Melmed, Long Chen, Narges Razavian, Seena Dehkharghani","submitted_at":"2026-06-12T21:02:09Z","abstract_excerpt":"Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic and fluid-sensitive T2-weighted (T2w) contrasts. However, methods for learning unified representations across the multitude of MRI contrast mechanisms at health-system scale are lacking. In this study, we introduce Neuro-JEPA, a sparse multimodal neuroimaging foundation model that combines a latent predictive objective with a Mixture-of-Experts architecture to encode brain MRI across core T1w, T2w, and fluid-suppressed FLAIR imaging (FLAIR). We furth"},"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":"2606.14957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-12T21:02:09Z","cross_cats_sorted":[],"title_canon_sha256":"da8048332eda0fbab58e9f78a12c3f3cc2a55d6776348ede8a69a513c39d04c5","abstract_canon_sha256":"d645b57bd6175870e509471fd733c1add3543946a6cfc6ae9af86e3641802193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:56.025618Z","signature_b64":"7hsdq3FG1Mt1alEtamcf06ZGkpg9wSkQQsuc/coi37EZrn0gReMB3JEkRs4EiYeeIrrQUKCNVi7vvBDtPZuHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dd1db0a0ceefa3f2579d768428efa9fd88b27d66db11e8c278bdfd9d7387e0c","last_reissued_at":"2026-06-19T16:12:56.025212Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:56.025212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Masurkar, Daniel Orringer, Haoxu Huang, James Ryan Loftus, Jennifer Frontera, Jingyun Chen, Jinu Hyun, Kara Melmed, Long Chen, Narges Razavian, Seena Dehkharghani","submitted_at":"2026-06-12T21:02:09Z","abstract_excerpt":"Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic and fluid-sensitive T2-weighted (T2w) contrasts. However, methods for learning unified representations across the multitude of MRI contrast mechanisms at health-system scale are lacking. In this study, we introduce Neuro-JEPA, a sparse multimodal neuroimaging foundation model that combines a latent predictive objective with a Mixture-of-Experts architecture to encode brain MRI across core T1w, T2w, and fluid-suppressed FLAIR imaging (FLAIR). We furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14957","kind":"arxiv","version":2},"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/2606.14957/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":"2606.14957","created_at":"2026-06-19T16:12:56.025278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.14957v2","created_at":"2026-06-19T16:12:56.025278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14957","created_at":"2026-06-19T16:12:56.025278+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXI5WCQM535D","created_at":"2026-06-19T16:12:56.025278+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXI5WCQM535D6JLZ","created_at":"2026-06-19T16:12:56.025278+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXI5WCQM","created_at":"2026-06-19T16:12:56.025278+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/LXI5WCQM535D6JLZ25UEFDX2T7","json":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7.json","graph_json":"https://pith.science/api/pith-number/LXI5WCQM535D6JLZ25UEFDX2T7/graph.json","events_json":"https://pith.science/api/pith-number/LXI5WCQM535D6JLZ25UEFDX2T7/events.json","paper":"https://pith.science/paper/LXI5WCQM"},"agent_actions":{"view_html":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7","download_json":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7.json","view_paper":"https://pith.science/paper/LXI5WCQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.14957&json=true","fetch_graph":"https://pith.science/api/pith-number/LXI5WCQM535D6JLZ25UEFDX2T7/graph.json","fetch_events":"https://pith.science/api/pith-number/LXI5WCQM535D6JLZ25UEFDX2T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7/action/storage_attestation","attest_author":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7/action/author_attestation","sign_citation":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7/action/citation_signature","submit_replication":"https://pith.science/pith/LXI5WCQM535D6JLZ25UEFDX2T7/action/replication_record"}},"created_at":"2026-06-19T16:12:56.025278+00:00","updated_at":"2026-06-19T16:12:56.025278+00:00"}