{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WRXYSN53TCCQBOVUKRT4PMTFDK","short_pith_number":"pith:WRXYSN53","schema_version":"1.0","canonical_sha256":"b46f8937bb988500bab45467c7b2651ab83eff3815b0f7a905714250d647e324","source":{"kind":"arxiv","id":"2509.09015","version":1},"attestation_state":"computed","paper":{"title":"VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenqian Le, Kushagra Yadav, Nikasadat Emami, Xujin \"Chris\" Liu, Xupeng Chen, Yao Wang, Yilin Zhao","submitted_at":"2025-09-10T21:20:17Z","abstract_excerpt":"Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scalability and practical deployment. We introduce \\textbf{VoxelFormer}, a lightweight transformer architecture that enables multi-subject training for visual decoding from fMRI. VoxelFormer integrates a Token Merging Transformer (ToMer) for efficient voxel compression and a query-driven Q-Former that produces fixed-size neural representations aligned with the CLIP image embedding space. Evaluated on the 7T Natural Scene"},"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":"2509.09015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T21:20:17Z","cross_cats_sorted":[],"title_canon_sha256":"db7c1bd2a584884489b95fa580a346502ba0a6a707519bb230165c7a34746cbe","abstract_canon_sha256":"7a115829f77c7d738b94eaa8326f0c3bd9a0aacc3889781c1278d514081e8b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:27.671164Z","signature_b64":"C+ASsnAoUOuass55fpfWLB6XphMjcCRRhi3QDSPnw/rn0lcH1AwHgdxkelSAiCrrYxej0Sv2UXyHyNa/ZzcyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b46f8937bb988500bab45467c7b2651ab83eff3815b0f7a905714250d647e324","last_reissued_at":"2026-07-05T12:09:27.670581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:27.670581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenqian Le, Kushagra Yadav, Nikasadat Emami, Xujin \"Chris\" Liu, Xupeng Chen, Yao Wang, Yilin Zhao","submitted_at":"2025-09-10T21:20:17Z","abstract_excerpt":"Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scalability and practical deployment. We introduce \\textbf{VoxelFormer}, a lightweight transformer architecture that enables multi-subject training for visual decoding from fMRI. VoxelFormer integrates a Token Merging Transformer (ToMer) for efficient voxel compression and a query-driven Q-Former that produces fixed-size neural representations aligned with the CLIP image embedding space. Evaluated on the 7T Natural Scene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09015","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/2509.09015/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":"2509.09015","created_at":"2026-07-05T12:09:27.670643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09015v1","created_at":"2026-07-05T12:09:27.670643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09015","created_at":"2026-07-05T12:09:27.670643+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRXYSN53TCCQ","created_at":"2026-07-05T12:09:27.670643+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRXYSN53TCCQBOVU","created_at":"2026-07-05T12:09:27.670643+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRXYSN53","created_at":"2026-07-05T12:09:27.670643+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/WRXYSN53TCCQBOVUKRT4PMTFDK","json":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK.json","graph_json":"https://pith.science/api/pith-number/WRXYSN53TCCQBOVUKRT4PMTFDK/graph.json","events_json":"https://pith.science/api/pith-number/WRXYSN53TCCQBOVUKRT4PMTFDK/events.json","paper":"https://pith.science/paper/WRXYSN53"},"agent_actions":{"view_html":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK","download_json":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK.json","view_paper":"https://pith.science/paper/WRXYSN53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09015&json=true","fetch_graph":"https://pith.science/api/pith-number/WRXYSN53TCCQBOVUKRT4PMTFDK/graph.json","fetch_events":"https://pith.science/api/pith-number/WRXYSN53TCCQBOVUKRT4PMTFDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK/action/storage_attestation","attest_author":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK/action/author_attestation","sign_citation":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK/action/citation_signature","submit_replication":"https://pith.science/pith/WRXYSN53TCCQBOVUKRT4PMTFDK/action/replication_record"}},"created_at":"2026-07-05T12:09:27.670643+00:00","updated_at":"2026-07-05T12:09:27.670643+00:00"}