{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CZVYUCBP2KAN2SWRXJZNHV4DRW","short_pith_number":"pith:CZVYUCBP","schema_version":"1.0","canonical_sha256":"166b8a082fd280dd4ad1ba72d3d7838d8140650cf651ee21f98bae702ad4908a","source":{"kind":"arxiv","id":"2212.02409","version":2},"attestation_state":"computed","paper":{"title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.CV","authors_text":"Amy Kuceyeski, Keith Jamison, Mert Sabuncu, Zijin Gu","submitted_at":"2022-12-05T16:47:19Z","abstract_excerpt":"Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we propose a novel approach for this task, which we call Cortex2Image, to decode visual stimuli with high semantic fidelity and rich fine-grained detail. In particular, we train a surface-based convolutional network model that maps from brain response to semantic image features first (Cortex2Semantic). We then combine this model with a high-quality image generator ("},"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":"2212.02409","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-05T16:47:19Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"593e62d2e9df3785c88da923c7ee981c4a6c10351cfb7efcfb47acc7d31e4395","abstract_canon_sha256":"ddd1f675d635ade18141e7e37cb5faa792c33af1dc0ccd095926dbb991cbac54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:04.177114Z","signature_b64":"JxJRL7fDln7PuehkULmOsgNdLfthYnFgI1N7loJhJ82pmN54TXyt9R+t5WRsfSNOSSRWlRCLY5PQGzOsnOjPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"166b8a082fd280dd4ad1ba72d3d7838d8140650cf651ee21f98bae702ad4908a","last_reissued_at":"2026-07-05T05:48:04.176567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:04.176567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.CV","authors_text":"Amy Kuceyeski, Keith Jamison, Mert Sabuncu, Zijin Gu","submitted_at":"2022-12-05T16:47:19Z","abstract_excerpt":"Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we propose a novel approach for this task, which we call Cortex2Image, to decode visual stimuli with high semantic fidelity and rich fine-grained detail. In particular, we train a surface-based convolutional network model that maps from brain response to semantic image features first (Cortex2Semantic). We then combine this model with a high-quality image generator ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02409","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/2212.02409/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":"2212.02409","created_at":"2026-07-05T05:48:04.176625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02409v2","created_at":"2026-07-05T05:48:04.176625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02409","created_at":"2026-07-05T05:48:04.176625+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZVYUCBP2KAN","created_at":"2026-07-05T05:48:04.176625+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZVYUCBP2KAN2SWR","created_at":"2026-07-05T05:48:04.176625+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZVYUCBP","created_at":"2026-07-05T05:48:04.176625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00121","citing_title":"Versatile Framework with Semantic and Structural guidance for Image Reconstruction from Brain Activity","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08495","citing_title":"NeuralBench: A Unifying Framework to Benchmark NeuroAI Models","ref_index":282,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW","json":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW.json","graph_json":"https://pith.science/api/pith-number/CZVYUCBP2KAN2SWRXJZNHV4DRW/graph.json","events_json":"https://pith.science/api/pith-number/CZVYUCBP2KAN2SWRXJZNHV4DRW/events.json","paper":"https://pith.science/paper/CZVYUCBP"},"agent_actions":{"view_html":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW","download_json":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW.json","view_paper":"https://pith.science/paper/CZVYUCBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02409&json=true","fetch_graph":"https://pith.science/api/pith-number/CZVYUCBP2KAN2SWRXJZNHV4DRW/graph.json","fetch_events":"https://pith.science/api/pith-number/CZVYUCBP2KAN2SWRXJZNHV4DRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW/action/storage_attestation","attest_author":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW/action/author_attestation","sign_citation":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW/action/citation_signature","submit_replication":"https://pith.science/pith/CZVYUCBP2KAN2SWRXJZNHV4DRW/action/replication_record"}},"created_at":"2026-07-05T05:48:04.176625+00:00","updated_at":"2026-07-05T05:48:04.176625+00:00"}