{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WEYI4PZVQPULLSYVVIJONGFDV4","short_pith_number":"pith:WEYI4PZV","schema_version":"1.0","canonical_sha256":"b1308e3f3583e8b5cb15aa12e698a3af0d6dbd0de1346834a0a0d068a07a4367","source":{"kind":"arxiv","id":"2312.07705","version":1},"attestation_state":"computed","paper":{"title":"Brain-optimized inference improves reconstructions of fMRI brain activity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Ghislain St-Yves, Jordyn Ojeda, Reese Kneeland, Thomas Naselaris","submitted_at":"2023-12-12T20:08:59Z","abstract_excerpt":"The release of large datasets and developments in AI have led to dramatic improvements in decoding methods that reconstruct seen images from human brain activity. We evaluate the prospect of further improving recent decoding methods by optimizing for consistency between reconstructions and brain activity during inference. We sample seed reconstructions from a base decoding method, then iteratively refine these reconstructions using a brain-optimized encoding model that maps images to brain activity. At each iteration, we sample a small library of images from an image distribution (a diffusion "},"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":"2312.07705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.NC","submitted_at":"2023-12-12T20:08:59Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"db7e2010ece0270724005de15e972a2bf28d754c38462c7b9535dbc0fad2a598","abstract_canon_sha256":"619cf3decac17fab54c1d83453ad7b4128ab383d941327849033f29c88654c31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:34.871910Z","signature_b64":"1BiaoaMaUBYlbMikZMWGe8Qkv6z/OeFJ5k32DQc+QnRVLGIBJTOq1HUmwXjor1eAFDMyCUD0YJ0X18LinzznDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1308e3f3583e8b5cb15aa12e698a3af0d6dbd0de1346834a0a0d068a07a4367","last_reissued_at":"2026-07-05T07:23:34.871492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:34.871492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Brain-optimized inference improves reconstructions of fMRI brain activity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Ghislain St-Yves, Jordyn Ojeda, Reese Kneeland, Thomas Naselaris","submitted_at":"2023-12-12T20:08:59Z","abstract_excerpt":"The release of large datasets and developments in AI have led to dramatic improvements in decoding methods that reconstruct seen images from human brain activity. We evaluate the prospect of further improving recent decoding methods by optimizing for consistency between reconstructions and brain activity during inference. We sample seed reconstructions from a base decoding method, then iteratively refine these reconstructions using a brain-optimized encoding model that maps images to brain activity. At each iteration, we sample a small library of images from an image distribution (a diffusion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07705","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/2312.07705/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":"2312.07705","created_at":"2026-07-05T07:23:34.871543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07705v1","created_at":"2026-07-05T07:23:34.871543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07705","created_at":"2026-07-05T07:23:34.871543+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEYI4PZVQPUL","created_at":"2026-07-05T07:23:34.871543+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEYI4PZVQPULLSYV","created_at":"2026-07-05T07:23:34.871543+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEYI4PZV","created_at":"2026-07-05T07:23:34.871543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17198","citing_title":"MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4","json":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4.json","graph_json":"https://pith.science/api/pith-number/WEYI4PZVQPULLSYVVIJONGFDV4/graph.json","events_json":"https://pith.science/api/pith-number/WEYI4PZVQPULLSYVVIJONGFDV4/events.json","paper":"https://pith.science/paper/WEYI4PZV"},"agent_actions":{"view_html":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4","download_json":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4.json","view_paper":"https://pith.science/paper/WEYI4PZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07705&json=true","fetch_graph":"https://pith.science/api/pith-number/WEYI4PZVQPULLSYVVIJONGFDV4/graph.json","fetch_events":"https://pith.science/api/pith-number/WEYI4PZVQPULLSYVVIJONGFDV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4/action/storage_attestation","attest_author":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4/action/author_attestation","sign_citation":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4/action/citation_signature","submit_replication":"https://pith.science/pith/WEYI4PZVQPULLSYVVIJONGFDV4/action/replication_record"}},"created_at":"2026-07-05T07:23:34.871543+00:00","updated_at":"2026-07-05T07:23:34.871543+00:00"}