{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JFDYYYSNH35XUEUBZ6NBHFTFCL","short_pith_number":"pith:JFDYYYSN","schema_version":"1.0","canonical_sha256":"49478c624d3efb7a1281cf9a13966512e6e02436bbbc9e90b1135f65a73cef89","source":{"kind":"arxiv","id":"2308.07428","version":1},"attestation_state":"computed","paper":{"title":"UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Weijian Mai, Zhijun Zhang","submitted_at":"2023-08-14T19:49:29Z","abstract_excerpt":"Image reconstruction and captioning from brain activity evoked by visual stimuli allow researchers to further understand the connection between the human brain and the visual perception system. While deep generative models have recently been employed in this field, reconstructing realistic captions and images with both low-level details and high semantic fidelity is still a challenging problem. In this work, we propose UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity. For the first time, we unify image reconstruction and captioning from v"},"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":"2308.07428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-14T19:49:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fdffa750849dfe4c0786bb5a42dfdbaf218b177f8d24488473a400b39f50e39","abstract_canon_sha256":"6cbea459babaf2bf8001a80b382a0746e14766dffac5e7b48ca5bdef7dae8f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:25.140707Z","signature_b64":"g1DgNM1rrHaZi8k8AnXnpIxTK+iuCN/9XognF9XdQIknD3N+q/Do9NLikNz2HJyTJGJParhEl1JMaPbgTrH4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49478c624d3efb7a1281cf9a13966512e6e02436bbbc9e90b1135f65a73cef89","last_reissued_at":"2026-07-05T06:41:25.140193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:25.140193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Weijian Mai, Zhijun Zhang","submitted_at":"2023-08-14T19:49:29Z","abstract_excerpt":"Image reconstruction and captioning from brain activity evoked by visual stimuli allow researchers to further understand the connection between the human brain and the visual perception system. While deep generative models have recently been employed in this field, reconstructing realistic captions and images with both low-level details and high semantic fidelity is still a challenging problem. In this work, we propose UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity. For the first time, we unify image reconstruction and captioning from v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07428","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/2308.07428/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":"2308.07428","created_at":"2026-07-05T06:41:25.140259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07428v1","created_at":"2026-07-05T06:41:25.140259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07428","created_at":"2026-07-05T06:41:25.140259+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFDYYYSNH35X","created_at":"2026-07-05T06:41:25.140259+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFDYYYSNH35XUEUB","created_at":"2026-07-05T06:41:25.140259+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFDYYYSN","created_at":"2026-07-05T06:41:25.140259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24679","citing_title":"MindAdapter: Few-Shot Parameter-Efficient Residual Calibration of Cross-Subject Brain-to-Visual Decoding Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30319","citing_title":"BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29588","citing_title":"Brain-IT-VQA: From Brain Signals to Answers","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17198","citing_title":"MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09817","citing_title":"NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08537","citing_title":"Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02586","citing_title":"StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL","json":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL.json","graph_json":"https://pith.science/api/pith-number/JFDYYYSNH35XUEUBZ6NBHFTFCL/graph.json","events_json":"https://pith.science/api/pith-number/JFDYYYSNH35XUEUBZ6NBHFTFCL/events.json","paper":"https://pith.science/paper/JFDYYYSN"},"agent_actions":{"view_html":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL","download_json":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL.json","view_paper":"https://pith.science/paper/JFDYYYSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07428&json=true","fetch_graph":"https://pith.science/api/pith-number/JFDYYYSNH35XUEUBZ6NBHFTFCL/graph.json","fetch_events":"https://pith.science/api/pith-number/JFDYYYSNH35XUEUBZ6NBHFTFCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL/action/storage_attestation","attest_author":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL/action/author_attestation","sign_citation":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL/action/citation_signature","submit_replication":"https://pith.science/pith/JFDYYYSNH35XUEUBZ6NBHFTFCL/action/replication_record"}},"created_at":"2026-07-05T06:41:25.140259+00:00","updated_at":"2026-07-05T06:41:25.140259+00:00"}