{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SIUHL66CFN6JPCNTNP5IVMIORF","short_pith_number":"pith:SIUHL66C","schema_version":"1.0","canonical_sha256":"922875fbc22b7c9789b36bfa8ab10e896af8d18bc33f782bfac4921e077029f7","source":{"kind":"arxiv","id":"2507.17958","version":2},"attestation_state":"computed","paper":{"title":"VIBE: Video-Input Brain Encoder for fMRI Response Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandr Shpilevoi, Andrej Bicanski, Daniel Carlstr\\\"om Schad, Janis Keck, Shrey Dixit, Viktor Studenyak","submitted_at":"2025-07-23T22:02:56Z","abstract_excerpt":"We present VIBE, a two-stage Transformer that fuses multi-modal video, audio, and text features to predict fMRI activity. Representations from open-source models (Qwen2.5, BEATs, Whisper, SlowFast, V-JEPA) are merged by a modality-fusion transformer and temporally decoded by a prediction transformer with rotary embeddings. Trained on 65 hours of movie data from the CNeuroMod dataset and ensembled across 20 seeds, VIBE attains mean parcel-wise Pearson correlations of 0.3225 on in-distribution Friends S07 and 0.2125 on six out-of-distribution films. An earlier iteration of the same architecture "},"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":"2507.17958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T22:02:56Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0c593f5d04085eb08cad7c39b9443677ffe87d58b76e77cbaa41fc931ac253a4","abstract_canon_sha256":"76532eaed94914a578a7550ffe257cb27040bac006dbb18679fb3ec257296e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:55.540133Z","signature_b64":"IIHrxqCKLGyRyOrklkNFo5gcNxqE7PVZ3VUVE0nxog2GhrlisySke8Iw6Z1rny0qsShu1calZ1R9CCls3HMHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"922875fbc22b7c9789b36bfa8ab10e896af8d18bc33f782bfac4921e077029f7","last_reissued_at":"2026-07-05T11:42:55.539650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:55.539650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIBE: Video-Input Brain Encoder for fMRI Response Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandr Shpilevoi, Andrej Bicanski, Daniel Carlstr\\\"om Schad, Janis Keck, Shrey Dixit, Viktor Studenyak","submitted_at":"2025-07-23T22:02:56Z","abstract_excerpt":"We present VIBE, a two-stage Transformer that fuses multi-modal video, audio, and text features to predict fMRI activity. Representations from open-source models (Qwen2.5, BEATs, Whisper, SlowFast, V-JEPA) are merged by a modality-fusion transformer and temporally decoded by a prediction transformer with rotary embeddings. Trained on 65 hours of movie data from the CNeuroMod dataset and ensembled across 20 seeds, VIBE attains mean parcel-wise Pearson correlations of 0.3225 on in-distribution Friends S07 and 0.2125 on six out-of-distribution films. An earlier iteration of the same architecture "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17958","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/2507.17958/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":"2507.17958","created_at":"2026-07-05T11:42:55.539711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17958v2","created_at":"2026-07-05T11:42:55.539711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17958","created_at":"2026-07-05T11:42:55.539711+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIUHL66CFN6J","created_at":"2026-07-05T11:42:55.539711+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIUHL66CFN6JPCNT","created_at":"2026-07-05T11:42:55.539711+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIUHL66C","created_at":"2026-07-05T11:42:55.539711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09770","citing_title":"Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29850","citing_title":"MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04326","citing_title":"A foundation model of vision, audition, and language for in-silico neuroscience","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF","json":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF.json","graph_json":"https://pith.science/api/pith-number/SIUHL66CFN6JPCNTNP5IVMIORF/graph.json","events_json":"https://pith.science/api/pith-number/SIUHL66CFN6JPCNTNP5IVMIORF/events.json","paper":"https://pith.science/paper/SIUHL66C"},"agent_actions":{"view_html":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF","download_json":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF.json","view_paper":"https://pith.science/paper/SIUHL66C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17958&json=true","fetch_graph":"https://pith.science/api/pith-number/SIUHL66CFN6JPCNTNP5IVMIORF/graph.json","fetch_events":"https://pith.science/api/pith-number/SIUHL66CFN6JPCNTNP5IVMIORF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF/action/storage_attestation","attest_author":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF/action/author_attestation","sign_citation":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF/action/citation_signature","submit_replication":"https://pith.science/pith/SIUHL66CFN6JPCNTNP5IVMIORF/action/replication_record"}},"created_at":"2026-07-05T11:42:55.539711+00:00","updated_at":"2026-07-05T11:42:55.539711+00:00"}