{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AWA43677ZDU4HG2534XN7LEVYR","short_pith_number":"pith:AWA43677","schema_version":"1.0","canonical_sha256":"0581cdfbffc8e9c39b5ddf2edfac95c4542d1a1bf2c89783c0dd8efa6d6a7bec","source":{"kind":"arxiv","id":"2606.29949","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"eess.IV","authors_text":"Christian Gebbe, Dominik Vonficht, Dominik Winter, Lo\\\"ic Le Bescond, Marco Rosati, Markus Schick, Nicolas Brieu, Richard J. Chen, Ross Stewart","submitted_at":"2026-06-29T08:24:53Z","abstract_excerpt":"H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides transcriptome-wide resolution at high cost with limited archival availability. We show that training a lightweight alignment module atop frozen histopathology and RNA-Seq foundation models enables open-vocabulary molecular prompting -- querying H&E slides with gene-set signatures to predict pathway activity without sequencing or end-to-end retraining. Using contrastive learning on a multi-cancer cohort (N=1,720), we achieve a 25-fold improvement "},"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":"2606.29949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2026-06-29T08:24:53Z","cross_cats_sorted":["cs.AI","q-bio.GN"],"title_canon_sha256":"33814c9f9cd4de353bf5caff549e041b423e8918316657cd80cce13f60e667d5","abstract_canon_sha256":"73682608758b203783baef7da92556cf4dc428f59898c0142d94215b96371a43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:42.334239Z","signature_b64":"W1mLCSze7rQETEa9P9a2l1DbDldp0wr6V0SBjykcxCHkuVH8gy4knBRX0qM3q+wxuPI8ISdrGrM9EXKigGBNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0581cdfbffc8e9c39b5ddf2edfac95c4542d1a1bf2c89783c0dd8efa6d6a7bec","last_reissued_at":"2026-06-30T02:17:42.333566Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:42.333566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"eess.IV","authors_text":"Christian Gebbe, Dominik Vonficht, Dominik Winter, Lo\\\"ic Le Bescond, Marco Rosati, Markus Schick, Nicolas Brieu, Richard J. Chen, Ross Stewart","submitted_at":"2026-06-29T08:24:53Z","abstract_excerpt":"H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides transcriptome-wide resolution at high cost with limited archival availability. We show that training a lightweight alignment module atop frozen histopathology and RNA-Seq foundation models enables open-vocabulary molecular prompting -- querying H&E slides with gene-set signatures to predict pathway activity without sequencing or end-to-end retraining. Using contrastive learning on a multi-cancer cohort (N=1,720), we achieve a 25-fold improvement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29949","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/2606.29949/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":"2606.29949","created_at":"2026-06-30T02:17:42.333643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29949v1","created_at":"2026-06-30T02:17:42.333643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29949","created_at":"2026-06-30T02:17:42.333643+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWA43677ZDU4","created_at":"2026-06-30T02:17:42.333643+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWA43677ZDU4HG25","created_at":"2026-06-30T02:17:42.333643+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWA43677","created_at":"2026-06-30T02:17:42.333643+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/AWA43677ZDU4HG2534XN7LEVYR","json":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR.json","graph_json":"https://pith.science/api/pith-number/AWA43677ZDU4HG2534XN7LEVYR/graph.json","events_json":"https://pith.science/api/pith-number/AWA43677ZDU4HG2534XN7LEVYR/events.json","paper":"https://pith.science/paper/AWA43677"},"agent_actions":{"view_html":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR","download_json":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR.json","view_paper":"https://pith.science/paper/AWA43677","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29949&json=true","fetch_graph":"https://pith.science/api/pith-number/AWA43677ZDU4HG2534XN7LEVYR/graph.json","fetch_events":"https://pith.science/api/pith-number/AWA43677ZDU4HG2534XN7LEVYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR/action/storage_attestation","attest_author":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR/action/author_attestation","sign_citation":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR/action/citation_signature","submit_replication":"https://pith.science/pith/AWA43677ZDU4HG2534XN7LEVYR/action/replication_record"}},"created_at":"2026-06-30T02:17:42.333643+00:00","updated_at":"2026-06-30T02:17:42.333643+00:00"}