{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MKBHQWEO7FRRBFXIWF4YGX4BOY","short_pith_number":"pith:MKBHQWEO","schema_version":"1.0","canonical_sha256":"628278588ef9631096e8b179835f8176049cb955e90089ade1da166e3a7b9187","source":{"kind":"arxiv","id":"2502.18725","version":1},"attestation_state":"computed","paper":{"title":"Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Jingxin Nie, Xin Liu, Ziyue Zhang","submitted_at":"2025-02-26T00:40:28Z","abstract_excerpt":"Traditional psychological experiments utilizing naturalistic stimuli face challenges in manual annotation and ecological validity. To address this, we introduce a novel paradigm leveraging multimodal large language models (LLMs) as proxies to extract rich semantic information from naturalistic images through a Visual Question Answering (VQA) strategy for analyzing human visual semantic representation. LLM-derived representations successfully predict established neural activity patterns measured by fMRI (e.g., faces, buildings), validating its feasibility and revealing hierarchical semantic org"},"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":"2502.18725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-26T00:40:28Z","cross_cats_sorted":["cs.CL","q-bio.NC"],"title_canon_sha256":"1bf4ff3af16c8e1ffc1389b98d8008b1c82a32557fea6169cb40c727fd6efe9b","abstract_canon_sha256":"3c43ebb48e2b1e0cde8393abc3f9761a6c4685f1bcc4b9f54e508d5f9a9b6f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:21.165076Z","signature_b64":"Q0+IdPmVHqUYSGfL+lns8MI+fOiixQ0YZTYHtZ3P+7QMoZOsQuUJZGZREFq8V/CXxwPH6i/Bv0/6/ir0J5ToAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"628278588ef9631096e8b179835f8176049cb955e90089ade1da166e3a7b9187","last_reissued_at":"2026-07-05T10:20:21.164558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:21.164558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Jingxin Nie, Xin Liu, Ziyue Zhang","submitted_at":"2025-02-26T00:40:28Z","abstract_excerpt":"Traditional psychological experiments utilizing naturalistic stimuli face challenges in manual annotation and ecological validity. To address this, we introduce a novel paradigm leveraging multimodal large language models (LLMs) as proxies to extract rich semantic information from naturalistic images through a Visual Question Answering (VQA) strategy for analyzing human visual semantic representation. LLM-derived representations successfully predict established neural activity patterns measured by fMRI (e.g., faces, buildings), validating its feasibility and revealing hierarchical semantic org"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18725","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/2502.18725/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":"2502.18725","created_at":"2026-07-05T10:20:21.164619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18725v1","created_at":"2026-07-05T10:20:21.164619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18725","created_at":"2026-07-05T10:20:21.164619+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKBHQWEO7FRR","created_at":"2026-07-05T10:20:21.164619+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKBHQWEO7FRRBFXI","created_at":"2026-07-05T10:20:21.164619+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKBHQWEO","created_at":"2026-07-05T10:20:21.164619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09392","citing_title":"HyNeuralMap: Hyperbolic Mapping of Visual Semantics to Neural Hierarchies","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY","json":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY.json","graph_json":"https://pith.science/api/pith-number/MKBHQWEO7FRRBFXIWF4YGX4BOY/graph.json","events_json":"https://pith.science/api/pith-number/MKBHQWEO7FRRBFXIWF4YGX4BOY/events.json","paper":"https://pith.science/paper/MKBHQWEO"},"agent_actions":{"view_html":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY","download_json":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY.json","view_paper":"https://pith.science/paper/MKBHQWEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18725&json=true","fetch_graph":"https://pith.science/api/pith-number/MKBHQWEO7FRRBFXIWF4YGX4BOY/graph.json","fetch_events":"https://pith.science/api/pith-number/MKBHQWEO7FRRBFXIWF4YGX4BOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY/action/storage_attestation","attest_author":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY/action/author_attestation","sign_citation":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY/action/citation_signature","submit_replication":"https://pith.science/pith/MKBHQWEO7FRRBFXIWF4YGX4BOY/action/replication_record"}},"created_at":"2026-07-05T10:20:21.164619+00:00","updated_at":"2026-07-05T10:20:21.164619+00:00"}