{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IAKCONYB5FS5VEVDADFGH7DI4B","short_pith_number":"pith:IAKCONYB","schema_version":"1.0","canonical_sha256":"4014273701e965da92a300ca63fc68e0581ff7c1b4df4d0839a60691041e8b6f","source":{"kind":"arxiv","id":"2211.06956","version":3},"attestation_state":"computed","paper":{"title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxin Qing, Juan Helen Zhou, Tiange Xiang, Wan Lin Yue, Zijiao Chen","submitted_at":"2022-11-13T17:04:05Z","abstract_excerpt":"Decoding visual stimuli from brain recordings aims to deepen our understanding of the human visual system and build a solid foundation for bridging human and computer vision through the Brain-Computer Interface. However, reconstructing high-quality images with correct semantics from brain recordings is a challenging problem due to the complex underlying representations of brain signals and the scarcity of data annotations. In this work, we present MinD-Vis: Sparse Masked Brain Modeling with Double-Conditioned Latent Diffusion Model for Human Vision Decoding. Firstly, we learn an effective self"},"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":"2211.06956","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-13T17:04:05Z","cross_cats_sorted":[],"title_canon_sha256":"ff2f601a9a05f660378c755160edc7bae677103a9e4d53f26fb4ca66425cc3be","abstract_canon_sha256":"0cf6aca88bb36d7d77c701099c2eae162708d19b6fe707bf5552d4d869b84458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:00.993449Z","signature_b64":"qo3fLUNGHgo3ouEYCYfCYjLF63m2jdVmNt8k7rXSjwj6Yplhy/hCIAmuQMt7MOw35Hs23dJMNEeMQ1pMINjMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4014273701e965da92a300ca63fc68e0581ff7c1b4df4d0839a60691041e8b6f","last_reissued_at":"2026-07-05T05:56:00.992908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:00.992908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxin Qing, Juan Helen Zhou, Tiange Xiang, Wan Lin Yue, Zijiao Chen","submitted_at":"2022-11-13T17:04:05Z","abstract_excerpt":"Decoding visual stimuli from brain recordings aims to deepen our understanding of the human visual system and build a solid foundation for bridging human and computer vision through the Brain-Computer Interface. However, reconstructing high-quality images with correct semantics from brain recordings is a challenging problem due to the complex underlying representations of brain signals and the scarcity of data annotations. In this work, we present MinD-Vis: Sparse Masked Brain Modeling with Double-Conditioned Latent Diffusion Model for Human Vision Decoding. Firstly, we learn an effective self"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06956","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/2211.06956/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":"2211.06956","created_at":"2026-07-05T05:56:00.992973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06956v3","created_at":"2026-07-05T05:56:00.992973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06956","created_at":"2026-07-05T05:56:00.992973+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAKCONYB5FS5","created_at":"2026-07-05T05:56:00.992973+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAKCONYB5FS5VEVD","created_at":"2026-07-05T05:56:00.992973+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAKCONYB","created_at":"2026-07-05T05:56:00.992973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B","json":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B.json","graph_json":"https://pith.science/api/pith-number/IAKCONYB5FS5VEVDADFGH7DI4B/graph.json","events_json":"https://pith.science/api/pith-number/IAKCONYB5FS5VEVDADFGH7DI4B/events.json","paper":"https://pith.science/paper/IAKCONYB"},"agent_actions":{"view_html":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B","download_json":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B.json","view_paper":"https://pith.science/paper/IAKCONYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06956&json=true","fetch_graph":"https://pith.science/api/pith-number/IAKCONYB5FS5VEVDADFGH7DI4B/graph.json","fetch_events":"https://pith.science/api/pith-number/IAKCONYB5FS5VEVDADFGH7DI4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B/action/storage_attestation","attest_author":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B/action/author_attestation","sign_citation":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B/action/citation_signature","submit_replication":"https://pith.science/pith/IAKCONYB5FS5VEVDADFGH7DI4B/action/replication_record"}},"created_at":"2026-07-05T05:56:00.992973+00:00","updated_at":"2026-07-05T05:56:00.992973+00:00"}