{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SIUHL66CFN6JPCNTNP5IVMIORF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76532eaed94914a578a7550ffe257cb27040bac006dbb18679fb3ec257296e20","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T22:02:56Z","title_canon_sha256":"0c593f5d04085eb08cad7c39b9443677ffe87d58b76e77cbaa41fc931ac253a4"},"schema_version":"1.0","source":{"id":"2507.17958","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17958","created_at":"2026-07-05T11:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17958v2","created_at":"2026-07-05T11:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17958","created_at":"2026-07-05T11:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"SIUHL66CFN6J","created_at":"2026-07-05T11:42:55Z"},{"alias_kind":"pith_short_16","alias_value":"SIUHL66CFN6JPCNT","created_at":"2026-07-05T11:42:55Z"},{"alias_kind":"pith_short_8","alias_value":"SIUHL66C","created_at":"2026-07-05T11:42:55Z"}],"graph_snapshots":[{"event_id":"sha256:2abcd47f1e9a50db01ac22e435070c39a97650429df3f1083dc37c2236de9015","target":"graph","created_at":"2026-07-05T11:42:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.17958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aleksandr Shpilevoi, Andrej Bicanski, Daniel Carlstr\\\"om Schad, Janis Keck, Shrey Dixit, Viktor Studenyak","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T22:02:56Z","title":"VIBE: Video-Input Brain Encoder for fMRI Response Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17958","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bb20d12fd9a73df4fc80b893cd2efde743f1046e333d65ce9c2405c0875f9650","target":"record","created_at":"2026-07-05T11:42:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76532eaed94914a578a7550ffe257cb27040bac006dbb18679fb3ec257296e20","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T22:02:56Z","title_canon_sha256":"0c593f5d04085eb08cad7c39b9443677ffe87d58b76e77cbaa41fc931ac253a4"},"schema_version":"1.0","source":{"id":"2507.17958","kind":"arxiv","version":2}},"canonical_sha256":"922875fbc22b7c9789b36bfa8ab10e896af8d18bc33f782bfac4921e077029f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"922875fbc22b7c9789b36bfa8ab10e896af8d18bc33f782bfac4921e077029f7","first_computed_at":"2026-07-05T11:42:55.539650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:55.539650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IIHrxqCKLGyRyOrklkNFo5gcNxqE7PVZ3VUVE0nxog2GhrlisySke8Iw6Z1rny0qsShu1calZ1R9CCls3HMHAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:55.540133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17958","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb20d12fd9a73df4fc80b893cd2efde743f1046e333d65ce9c2405c0875f9650","sha256:2abcd47f1e9a50db01ac22e435070c39a97650429df3f1083dc37c2236de9015"],"state_sha256":"ffc8a760740b4b32fdf7424cf39460f6a6c6ced5a019e72884a221dbdea0f379"}