{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YVJDU5D2W7OVYEBLAWASJSZ3OW","short_pith_number":"pith:YVJDU5D2","schema_version":"1.0","canonical_sha256":"c5523a747ab7dd5c102b058124cb3b759f9be9d8cb574744fb67673e3c441a26","source":{"kind":"arxiv","id":"2502.15786","version":2},"attestation_state":"computed","paper":{"title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.SP"],"primary_cat":"q-bio.NC","authors_text":"Aosong Feng, Haoyu Hu, Rex Ying, Weikang Qiu, Yujun Yan, Zheng Huang","submitted_at":"2025-02-18T03:27:37Z","abstract_excerpt":"Decoding functional magnetic resonance imaging (fMRI) signals into text has been a key challenge in the neuroscience community, with the potential to advance brain-computer interfaces and uncover deeper insights into brain mechanisms. However, existing approaches often struggle with suboptimal predictive performance, limited task variety, and poor generalization across subjects. In response to this, we propose MindLLM, a model designed for subject-agnostic and versatile fMRI-to-text decoding. MindLLM consists of an fMRI encoder and an off-the-shelf LLM. The fMRI encoder employs a neuroscience-"},"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":"2502.15786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.NC","submitted_at":"2025-02-18T03:27:37Z","cross_cats_sorted":["cs.AI","cs.LG","eess.SP"],"title_canon_sha256":"72844679b06ac6926a85090e8997b52a53f8b04c55938cec1455bd59e6e2eb5f","abstract_canon_sha256":"b86f84eefacb822784a040b9b622e03ef86f31d834cade945e602a5e14305483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:41.797786Z","signature_b64":"/lJNsBSevE24UgTq+WjjHFRaQJ0Vhk+gD7q/xwLVuifyOFc9701kukWu2aI/zCDK7LjoFjT/F5+m4qdxk8+SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5523a747ab7dd5c102b058124cb3b759f9be9d8cb574744fb67673e3c441a26","last_reissued_at":"2026-07-05T11:17:41.797261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:41.797261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.SP"],"primary_cat":"q-bio.NC","authors_text":"Aosong Feng, Haoyu Hu, Rex Ying, Weikang Qiu, Yujun Yan, Zheng Huang","submitted_at":"2025-02-18T03:27:37Z","abstract_excerpt":"Decoding functional magnetic resonance imaging (fMRI) signals into text has been a key challenge in the neuroscience community, with the potential to advance brain-computer interfaces and uncover deeper insights into brain mechanisms. However, existing approaches often struggle with suboptimal predictive performance, limited task variety, and poor generalization across subjects. In response to this, we propose MindLLM, a model designed for subject-agnostic and versatile fMRI-to-text decoding. MindLLM consists of an fMRI encoder and an off-the-shelf LLM. The fMRI encoder employs a neuroscience-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15786","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/2502.15786/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":"2502.15786","created_at":"2026-07-05T11:17:41.797322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15786v2","created_at":"2026-07-05T11:17:41.797322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15786","created_at":"2026-07-05T11:17:41.797322+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVJDU5D2W7OV","created_at":"2026-07-05T11:17:41.797322+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVJDU5D2W7OVYEBL","created_at":"2026-07-05T11:17:41.797322+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVJDU5D2","created_at":"2026-07-05T11:17:41.797322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.21760","citing_title":"fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW","json":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW.json","graph_json":"https://pith.science/api/pith-number/YVJDU5D2W7OVYEBLAWASJSZ3OW/graph.json","events_json":"https://pith.science/api/pith-number/YVJDU5D2W7OVYEBLAWASJSZ3OW/events.json","paper":"https://pith.science/paper/YVJDU5D2"},"agent_actions":{"view_html":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW","download_json":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW.json","view_paper":"https://pith.science/paper/YVJDU5D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15786&json=true","fetch_graph":"https://pith.science/api/pith-number/YVJDU5D2W7OVYEBLAWASJSZ3OW/graph.json","fetch_events":"https://pith.science/api/pith-number/YVJDU5D2W7OVYEBLAWASJSZ3OW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW/action/storage_attestation","attest_author":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW/action/author_attestation","sign_citation":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW/action/citation_signature","submit_replication":"https://pith.science/pith/YVJDU5D2W7OVYEBLAWASJSZ3OW/action/replication_record"}},"created_at":"2026-07-05T11:17:41.797322+00:00","updated_at":"2026-07-05T11:17:41.797322+00:00"}