{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7SCIITEVLQPC3OR6ZFSS5XDKXR","short_pith_number":"pith:7SCIITEV","schema_version":"1.0","canonical_sha256":"fc84844c955c1e2dba3ec9652edc6abc4e30afa74bffab0e094b057265763736","source":{"kind":"arxiv","id":"2305.00556","version":2},"attestation_state":"computed","paper":{"title":"Reconstructing seen images from human brain activity via guided stochastic search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.IV"],"primary_cat":"q-bio.NC","authors_text":"Ghislain St-Yves, Jordyn Ojeda, Reese Kneeland, Thomas Naselaris","submitted_at":"2023-04-30T19:40:01Z","abstract_excerpt":"Visual reconstruction algorithms are an interpretive tool that map brain activity to pixels. Past reconstruction algorithms employed brute-force search through a massive library to select candidate images that, when passed through an encoding model, accurately predict brain activity. Here, we use conditional generative diffusion models to extend and improve this search-based strategy. We decode a semantic descriptor from human brain activity (7T fMRI) in voxels across most of visual cortex, then use a diffusion model to sample a small library of images conditioned on this descriptor. We pass e"},"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":"2305.00556","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.NC","submitted_at":"2023-04-30T19:40:01Z","cross_cats_sorted":["cs.CV","cs.LG","eess.IV"],"title_canon_sha256":"22ef8e47558a55b840678046057b20e716681177ac694c58728a6071fad675ec","abstract_canon_sha256":"f10890025d4dc3a87569cf3a2e66655d3ed6fe9a4f36849803205dc3a44a4cff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:19.880268Z","signature_b64":"LaMI9giRJ+LKzUp8BQFVHkjV6wFPnzZp8vtYavFAzgaxrXula5N91J9WiMM3xcL69I+s1DzQ4Rcpxb6jlMXvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc84844c955c1e2dba3ec9652edc6abc4e30afa74bffab0e094b057265763736","last_reissued_at":"2026-07-05T06:06:19.879873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:19.879873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconstructing seen images from human brain activity via guided stochastic search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.IV"],"primary_cat":"q-bio.NC","authors_text":"Ghislain St-Yves, Jordyn Ojeda, Reese Kneeland, Thomas Naselaris","submitted_at":"2023-04-30T19:40:01Z","abstract_excerpt":"Visual reconstruction algorithms are an interpretive tool that map brain activity to pixels. Past reconstruction algorithms employed brute-force search through a massive library to select candidate images that, when passed through an encoding model, accurately predict brain activity. Here, we use conditional generative diffusion models to extend and improve this search-based strategy. We decode a semantic descriptor from human brain activity (7T fMRI) in voxels across most of visual cortex, then use a diffusion model to sample a small library of images conditioned on this descriptor. We pass e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00556","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/2305.00556/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":"2305.00556","created_at":"2026-07-05T06:06:19.879937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00556v2","created_at":"2026-07-05T06:06:19.879937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00556","created_at":"2026-07-05T06:06:19.879937+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SCIITEVLQPC","created_at":"2026-07-05T06:06:19.879937+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SCIITEVLQPC3OR6","created_at":"2026-07-05T06:06:19.879937+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SCIITEV","created_at":"2026-07-05T06:06:19.879937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14556","citing_title":"Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRI","ref_index":2014,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR","json":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR.json","graph_json":"https://pith.science/api/pith-number/7SCIITEVLQPC3OR6ZFSS5XDKXR/graph.json","events_json":"https://pith.science/api/pith-number/7SCIITEVLQPC3OR6ZFSS5XDKXR/events.json","paper":"https://pith.science/paper/7SCIITEV"},"agent_actions":{"view_html":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR","download_json":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR.json","view_paper":"https://pith.science/paper/7SCIITEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00556&json=true","fetch_graph":"https://pith.science/api/pith-number/7SCIITEVLQPC3OR6ZFSS5XDKXR/graph.json","fetch_events":"https://pith.science/api/pith-number/7SCIITEVLQPC3OR6ZFSS5XDKXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR/action/storage_attestation","attest_author":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR/action/author_attestation","sign_citation":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR/action/citation_signature","submit_replication":"https://pith.science/pith/7SCIITEVLQPC3OR6ZFSS5XDKXR/action/replication_record"}},"created_at":"2026-07-05T06:06:19.879937+00:00","updated_at":"2026-07-05T06:06:19.879937+00:00"}