{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YERLA64Q7UBDH2PWFHRFKSA4AV","short_pith_number":"pith:YERLA64Q","schema_version":"1.0","canonical_sha256":"c122b07b90fd0233e9f629e255481c056db431527c0f25f54bc1a62bb399da4f","source":{"kind":"arxiv","id":"2403.11207","version":2},"attestation_state":"computed","paper":{"title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Ashutosh Narang, Cesar Kadir Torrico Villanueva, Charan Santhirasegaran, Jonathan Xu, Kenneth A. Norman, Mihir Tripathy, Paul S. Scotti, Reese Kneeland, Tanishq Mathew Abraham, Thomas Naselaris, Tong Chen","submitted_at":"2024-03-17T13:15:22Z","abstract_excerpt":"Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited. This is because such models are trained independently per subject where each subject requires dozens of hours of expensive fMRI training data to attain high-quality results. The present work showcases high-quality reconstructions using only 1 hour of fMRI training data. We pretrain our model across 7 subjects and then fine-tune on minimal data from a new subject. Our novel functional alignment procedure linearly maps all brain data to a shared-subject"},"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":"2403.11207","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T13:15:22Z","cross_cats_sorted":["cs.AI","q-bio.NC"],"title_canon_sha256":"7e0931c6c616196772cb43c9c29b4779f35139de473fede33f5898751c43a047","abstract_canon_sha256":"5cf2dab90c07f14e21d35eb45d907d530780e8566757f7445a1b7bb6ec3d4e57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:12.227819Z","signature_b64":"h1ej3kuPOOVIjX0oISW0SkkrkZeKSRrU+NltG4lRPoyeMdgHVp1x6qpgJomXWujSMzmlk9SFv3O/vKdeyDg0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c122b07b90fd0233e9f629e255481c056db431527c0f25f54bc1a62bb399da4f","last_reissued_at":"2026-07-05T08:32:12.227340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:12.227340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Ashutosh Narang, Cesar Kadir Torrico Villanueva, Charan Santhirasegaran, Jonathan Xu, Kenneth A. Norman, Mihir Tripathy, Paul S. Scotti, Reese Kneeland, Tanishq Mathew Abraham, Thomas Naselaris, Tong Chen","submitted_at":"2024-03-17T13:15:22Z","abstract_excerpt":"Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited. This is because such models are trained independently per subject where each subject requires dozens of hours of expensive fMRI training data to attain high-quality results. The present work showcases high-quality reconstructions using only 1 hour of fMRI training data. We pretrain our model across 7 subjects and then fine-tune on minimal data from a new subject. Our novel functional alignment procedure linearly maps all brain data to a shared-subject"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11207","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/2403.11207/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":"2403.11207","created_at":"2026-07-05T08:32:12.227392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11207v2","created_at":"2026-07-05T08:32:12.227392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11207","created_at":"2026-07-05T08:32:12.227392+00:00"},{"alias_kind":"pith_short_12","alias_value":"YERLA64Q7UBD","created_at":"2026-07-05T08:32:12.227392+00:00"},{"alias_kind":"pith_short_16","alias_value":"YERLA64Q7UBDH2PW","created_at":"2026-07-05T08:32:12.227392+00:00"},{"alias_kind":"pith_short_8","alias_value":"YERLA64Q","created_at":"2026-07-05T08:32:12.227392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19081","citing_title":"Retrieval-Based Brain Decoding by Alignment, not Complexity","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18667","citing_title":"Can neurons speak? Semantic narration of vision at single-cell resolution","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11500","citing_title":"FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04040","citing_title":"Channel-Oriented Design for EEG-to-Music Reconstruction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24523","citing_title":"MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30319","citing_title":"BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29588","citing_title":"Brain-IT-VQA: From Brain Signals to Answers","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23895","citing_title":"From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19279","citing_title":"FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21671","citing_title":"Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21740","citing_title":"A cross-species neural foundation model for end-to-end speech decoding","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14569","citing_title":"Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction","ref_index":81,"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":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04309","citing_title":"Interpreting V1 Population Activity via Image-Neural Latent Representation Alignment","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04680","citing_title":"Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10617","citing_title":"Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09817","citing_title":"NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08537","citing_title":"Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV","json":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV.json","graph_json":"https://pith.science/api/pith-number/YERLA64Q7UBDH2PWFHRFKSA4AV/graph.json","events_json":"https://pith.science/api/pith-number/YERLA64Q7UBDH2PWFHRFKSA4AV/events.json","paper":"https://pith.science/paper/YERLA64Q"},"agent_actions":{"view_html":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV","download_json":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV.json","view_paper":"https://pith.science/paper/YERLA64Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11207&json=true","fetch_graph":"https://pith.science/api/pith-number/YERLA64Q7UBDH2PWFHRFKSA4AV/graph.json","fetch_events":"https://pith.science/api/pith-number/YERLA64Q7UBDH2PWFHRFKSA4AV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV/action/storage_attestation","attest_author":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV/action/author_attestation","sign_citation":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV/action/citation_signature","submit_replication":"https://pith.science/pith/YERLA64Q7UBDH2PWFHRFKSA4AV/action/replication_record"}},"created_at":"2026-07-05T08:32:12.227392+00:00","updated_at":"2026-07-05T08:32:12.227392+00:00"}