{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SFYFFBU2KM6KAKIDIHCZAAATRW","short_pith_number":"pith:SFYFFBU2","schema_version":"1.0","canonical_sha256":"917052869a533ca0290341c59000138dac5c2f45f547cb921c15c6179676ef32","source":{"kind":"arxiv","id":"2511.11437","version":2},"attestation_state":"computed","paper":{"title":"Hi-DREAM: Brain-Inspired Hierarchical Diffusion for fMRI-to-Image Reconstruction via ROI Encoder and VisuAl Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Adeel Razi, Dinh Phung, Guowei Zhang, Kai Sun, Levin Kuhlmann, Moein Khajehnejad, Yun Zhao","submitted_at":"2025-11-14T16:05:44Z","abstract_excerpt":"Reconstructing natural images from fMRI requires bridging neural activity with both the structural and semantic representations used by modern generative models. Existing diffusion-based decoders often condition on a single global fMRI embedding, which limits their ability to exploit the hierarchical organization of the visual cortex and makes the contribution of different visual areas difficult to inspect. We propose Hi-DREAM, a brain-inspired hierarchical diffusion framework that structures fMRI conditioning according to early, middle, and late visual Regions of Interest (ROI) streams. A ROI"},"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":"2511.11437","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-14T16:05:44Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"e5bf296120e738be461ac26b6293dbb5d7b389dbb60b0e3f11e2dd2217a600a3","abstract_canon_sha256":"2c9a22edc126714304fd30e9215eecb3e9e290ddb8c1a59f610c016778c4fcab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:14.836809Z","signature_b64":"AE9Fg1DhfHSwGAqHXnnm1m14MPZ9KTg1nR1B8lauKY5ppuRnYGVr4wKaX/oxCDHcGcfjcrKajwQqejnEZ7txCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917052869a533ca0290341c59000138dac5c2f45f547cb921c15c6179676ef32","last_reissued_at":"2026-07-03T01:17:14.836310Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:14.836310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-DREAM: Brain-Inspired Hierarchical Diffusion for fMRI-to-Image Reconstruction via ROI Encoder and VisuAl Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Adeel Razi, Dinh Phung, Guowei Zhang, Kai Sun, Levin Kuhlmann, Moein Khajehnejad, Yun Zhao","submitted_at":"2025-11-14T16:05:44Z","abstract_excerpt":"Reconstructing natural images from fMRI requires bridging neural activity with both the structural and semantic representations used by modern generative models. Existing diffusion-based decoders often condition on a single global fMRI embedding, which limits their ability to exploit the hierarchical organization of the visual cortex and makes the contribution of different visual areas difficult to inspect. We propose Hi-DREAM, a brain-inspired hierarchical diffusion framework that structures fMRI conditioning according to early, middle, and late visual Regions of Interest (ROI) streams. A ROI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.11437","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/2511.11437/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":"2511.11437","created_at":"2026-07-03T01:17:14.836389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.11437v2","created_at":"2026-07-03T01:17:14.836389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.11437","created_at":"2026-07-03T01:17:14.836389+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFYFFBU2KM6K","created_at":"2026-07-03T01:17:14.836389+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFYFFBU2KM6KAKID","created_at":"2026-07-03T01:17:14.836389+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFYFFBU2","created_at":"2026-07-03T01:17:14.836389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.09392","citing_title":"HyNeuralMap: Hyperbolic Mapping of Visual Semantics to Neural Hierarchies","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW","json":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW.json","graph_json":"https://pith.science/api/pith-number/SFYFFBU2KM6KAKIDIHCZAAATRW/graph.json","events_json":"https://pith.science/api/pith-number/SFYFFBU2KM6KAKIDIHCZAAATRW/events.json","paper":"https://pith.science/paper/SFYFFBU2"},"agent_actions":{"view_html":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW","download_json":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW.json","view_paper":"https://pith.science/paper/SFYFFBU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.11437&json=true","fetch_graph":"https://pith.science/api/pith-number/SFYFFBU2KM6KAKIDIHCZAAATRW/graph.json","fetch_events":"https://pith.science/api/pith-number/SFYFFBU2KM6KAKIDIHCZAAATRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW/action/storage_attestation","attest_author":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW/action/author_attestation","sign_citation":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW/action/citation_signature","submit_replication":"https://pith.science/pith/SFYFFBU2KM6KAKIDIHCZAAATRW/action/replication_record"}},"created_at":"2026-07-03T01:17:14.836389+00:00","updated_at":"2026-07-03T01:17:14.836389+00:00"}