{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CWPPJXI2QBZINZMQD55VS2XHAU","short_pith_number":"pith:CWPPJXI2","schema_version":"1.0","canonical_sha256":"159ef4dd1a807286e5901f7b596ae7050bd6e2fe45c4db65375d10606474fe15","source":{"kind":"arxiv","id":"2608.08366","version":1},"attestation_state":"computed","paper":{"title":"VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.CV","authors_text":"Chenzi Ouyang, Haoxuan Zeng, Jie Liu, Kai Liu, Meiqi Zhu, Shuibing Chen, Suyuan Wang, Xin Luo, Yicheng Tao","submitted_at":"2026-08-08T23:36:00Z","abstract_excerpt":"Spatial transcriptomics can resolve gene expression at single-cell resolution, but it is costly, limited to targeted panels of a few hundred to a few thousand genes, and applicable to only a small number of samples. H&E imaging, by contrast, is cheap and collected routinely at scale. This makes predicting single-cell expression directly from morphology a practical way to bring molecular analysis to large tissue archives. We therefore present VOICE, a multimodal foundation model that predicts single-cell gene expression from H&E images using paired Xenium data. VOICE first aligns cell centered "},"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":"2608.08366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T23:36:00Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"db1287b7a1b55d2eb22c28ea49c25cea054f4defb128567d7670062a9e592131","abstract_canon_sha256":"37174391b9e4f47c87e4f80e27ef98f9d31bc89d41d741da1a5bc3195245f30d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:26.242224Z","signature_b64":"c8AsI3H0jFx0tW1VrLFj5omlSN+YNeK/pXp++MGhW1AaF2EBBYrrzQu8hVI74EXw968aTkafLNgFnFLmhy2lAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"159ef4dd1a807286e5901f7b596ae7050bd6e2fe45c4db65375d10606474fe15","last_reissued_at":"2026-08-11T01:22:26.239868Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:26.239868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.CV","authors_text":"Chenzi Ouyang, Haoxuan Zeng, Jie Liu, Kai Liu, Meiqi Zhu, Shuibing Chen, Suyuan Wang, Xin Luo, Yicheng Tao","submitted_at":"2026-08-08T23:36:00Z","abstract_excerpt":"Spatial transcriptomics can resolve gene expression at single-cell resolution, but it is costly, limited to targeted panels of a few hundred to a few thousand genes, and applicable to only a small number of samples. H&E imaging, by contrast, is cheap and collected routinely at scale. This makes predicting single-cell expression directly from morphology a practical way to bring molecular analysis to large tissue archives. We therefore present VOICE, a multimodal foundation model that predicts single-cell gene expression from H&E images using paired Xenium data. VOICE first aligns cell centered "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08366","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/2608.08366/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":"2608.08366","created_at":"2026-08-11T01:22:26.240590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08366v1","created_at":"2026-08-11T01:22:26.240590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08366","created_at":"2026-08-11T01:22:26.240590+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWPPJXI2QBZI","created_at":"2026-08-11T01:22:26.240590+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWPPJXI2QBZINZMQ","created_at":"2026-08-11T01:22:26.240590+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWPPJXI2","created_at":"2026-08-11T01:22:26.240590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU","json":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU.json","graph_json":"https://pith.science/api/pith-number/CWPPJXI2QBZINZMQD55VS2XHAU/graph.json","events_json":"https://pith.science/api/pith-number/CWPPJXI2QBZINZMQD55VS2XHAU/events.json","paper":"https://pith.science/paper/CWPPJXI2"},"agent_actions":{"view_html":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU","download_json":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU.json","view_paper":"https://pith.science/paper/CWPPJXI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08366&json=true","fetch_graph":"https://pith.science/api/pith-number/CWPPJXI2QBZINZMQD55VS2XHAU/graph.json","fetch_events":"https://pith.science/api/pith-number/CWPPJXI2QBZINZMQD55VS2XHAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU/action/storage_attestation","attest_author":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU/action/author_attestation","sign_citation":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU/action/citation_signature","submit_replication":"https://pith.science/pith/CWPPJXI2QBZINZMQD55VS2XHAU/action/replication_record"}},"created_at":"2026-08-11T01:22:26.240590+00:00","updated_at":"2026-08-11T01:22:26.240590+00:00"}