{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MNZATDPWC7BO652CMXIOBUGXIU","short_pith_number":"pith:MNZATDPW","schema_version":"1.0","canonical_sha256":"6372098df617c2ef774265d0e0d0d7451bd6a331c44596bda2ba132543be6cef","source":{"kind":"arxiv","id":"2302.12971","version":3},"attestation_state":"computed","paper":{"title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Guibo Zhu, Nanning Zheng, Wei Zhou, Yongqiang Ma, Yulong Liu","submitted_at":"2023-02-25T03:28:54Z","abstract_excerpt":"Due to the lack of paired samples and the low signal-to-noise ratio of functional MRI (fMRI) signals, reconstructing perceived natural images or decoding their semantic contents from fMRI data are challenging tasks. In this work, we propose, for the first time, a task-agnostic fMRI-based brain decoding model, BrainCLIP, which leverages CLIP's cross-modal generalization ability to bridge the modality gap between brain activity, image, and text. Our experiments demonstrate that CLIP can act as a pivot for generic brain decoding tasks, including zero-shot visual categories decoding, fMRI-image/te"},"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":"2302.12971","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-25T03:28:54Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"b6c461afd79cb54799d4b113a18d75e4c30cecaf15aedebd4e9b57ce107ee6ad","abstract_canon_sha256":"72941a32e1df4f1a7f224824a01fae27d8da948d68bbc74f518c861800b462dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:48.764153Z","signature_b64":"weIp3nEdvIpK4bPUDwdDTQRAennIX9Sh+oCPo6IMmPLWkhrKPEn7g7Dmak7XKiVZ3BgQh2QEYZtboR5TGeX1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6372098df617c2ef774265d0e0d0d7451bd6a331c44596bda2ba132543be6cef","last_reissued_at":"2026-07-05T06:09:48.763680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:48.763680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Guibo Zhu, Nanning Zheng, Wei Zhou, Yongqiang Ma, Yulong Liu","submitted_at":"2023-02-25T03:28:54Z","abstract_excerpt":"Due to the lack of paired samples and the low signal-to-noise ratio of functional MRI (fMRI) signals, reconstructing perceived natural images or decoding their semantic contents from fMRI data are challenging tasks. In this work, we propose, for the first time, a task-agnostic fMRI-based brain decoding model, BrainCLIP, which leverages CLIP's cross-modal generalization ability to bridge the modality gap between brain activity, image, and text. Our experiments demonstrate that CLIP can act as a pivot for generic brain decoding tasks, including zero-shot visual categories decoding, fMRI-image/te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12971","kind":"arxiv","version":3},"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/2302.12971/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":"2302.12971","created_at":"2026-07-05T06:09:48.763738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12971v3","created_at":"2026-07-05T06:09:48.763738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12971","created_at":"2026-07-05T06:09:48.763738+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNZATDPWC7BO","created_at":"2026-07-05T06:09:48.763738+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNZATDPWC7BO652C","created_at":"2026-07-05T06:09:48.763738+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNZATDPW","created_at":"2026-07-05T06:09:48.763738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19081","citing_title":"Retrieval-Based Brain Decoding by Alignment, not Complexity","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18667","citing_title":"Can neurons speak? Semantic narration of vision at single-cell resolution","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20525","citing_title":"NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding","ref_index":46,"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":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09817","citing_title":"NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08537","citing_title":"Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU","json":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU.json","graph_json":"https://pith.science/api/pith-number/MNZATDPWC7BO652CMXIOBUGXIU/graph.json","events_json":"https://pith.science/api/pith-number/MNZATDPWC7BO652CMXIOBUGXIU/events.json","paper":"https://pith.science/paper/MNZATDPW"},"agent_actions":{"view_html":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU","download_json":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU.json","view_paper":"https://pith.science/paper/MNZATDPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12971&json=true","fetch_graph":"https://pith.science/api/pith-number/MNZATDPWC7BO652CMXIOBUGXIU/graph.json","fetch_events":"https://pith.science/api/pith-number/MNZATDPWC7BO652CMXIOBUGXIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU/action/storage_attestation","attest_author":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU/action/author_attestation","sign_citation":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU/action/citation_signature","submit_replication":"https://pith.science/pith/MNZATDPWC7BO652CMXIOBUGXIU/action/replication_record"}},"created_at":"2026-07-05T06:09:48.763738+00:00","updated_at":"2026-07-05T06:09:48.763738+00:00"}