{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MIZYZMEN5H356CDAKKQCTWF4YC","short_pith_number":"pith:MIZYZMEN","schema_version":"1.0","canonical_sha256":"62338cb08de9f7df086052a029d8bcc09705a7610a3a2c82ee84267f995e3d27","source":{"kind":"arxiv","id":"2403.03891","version":1},"attestation_state":"computed","paper":{"title":"Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Daniel Truhn, Firas Khader, Georg W\\\"olflein, Jakob Nikolas Kather, Marko van Treeck, Marta Ligero, Omar S. M. El Nahhas, Tim Lenz","submitted_at":"2024-03-06T17:51:04Z","abstract_excerpt":"Deep Learning (DL) can predict biomarkers directly from digitized cancer histology in a weakly-supervised setting. Recently, the prediction of continuous biomarkers through regression-based DL has seen an increasing interest. Nonetheless, clinical decision making often requires a categorical outcome. Consequently, we developed a weakly-supervised joint multi-task Transformer architecture which has been trained and evaluated on four public patient cohorts for the prediction of two key predictive biomarkers, microsatellite instability (MSI) and homologous recombination deficiency (HRD), trained "},"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":"2403.03891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-03-06T17:51:04Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"ed8b7c32e5e9387a9991b6d81d9126149defbea0ff00b55a161e876dc2a46dbc","abstract_canon_sha256":"5905b5ad254b5df9dcb1789ecb7171a02642a23501e5a0fd854621714e3db5c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:02.756804Z","signature_b64":"11Keb9MuFhTbMQi2kBMV0GWhOB8AsGEl2w3XO5S5vWIMjuFGklqQyCKf7PnYKOzps9uKjPBbqvggMcD3+Nl+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62338cb08de9f7df086052a029d8bcc09705a7610a3a2c82ee84267f995e3d27","last_reissued_at":"2026-07-05T07:53:02.756342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:02.756342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Daniel Truhn, Firas Khader, Georg W\\\"olflein, Jakob Nikolas Kather, Marko van Treeck, Marta Ligero, Omar S. M. El Nahhas, Tim Lenz","submitted_at":"2024-03-06T17:51:04Z","abstract_excerpt":"Deep Learning (DL) can predict biomarkers directly from digitized cancer histology in a weakly-supervised setting. Recently, the prediction of continuous biomarkers through regression-based DL has seen an increasing interest. Nonetheless, clinical decision making often requires a categorical outcome. Consequently, we developed a weakly-supervised joint multi-task Transformer architecture which has been trained and evaluated on four public patient cohorts for the prediction of two key predictive biomarkers, microsatellite instability (MSI) and homologous recombination deficiency (HRD), trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03891","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/2403.03891/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":"2403.03891","created_at":"2026-07-05T07:53:02.756404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03891v1","created_at":"2026-07-05T07:53:02.756404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03891","created_at":"2026-07-05T07:53:02.756404+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIZYZMEN5H35","created_at":"2026-07-05T07:53:02.756404+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIZYZMEN5H356CDA","created_at":"2026-07-05T07:53:02.756404+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIZYZMEN","created_at":"2026-07-05T07:53:02.756404+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/MIZYZMEN5H356CDAKKQCTWF4YC","json":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC.json","graph_json":"https://pith.science/api/pith-number/MIZYZMEN5H356CDAKKQCTWF4YC/graph.json","events_json":"https://pith.science/api/pith-number/MIZYZMEN5H356CDAKKQCTWF4YC/events.json","paper":"https://pith.science/paper/MIZYZMEN"},"agent_actions":{"view_html":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC","download_json":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC.json","view_paper":"https://pith.science/paper/MIZYZMEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03891&json=true","fetch_graph":"https://pith.science/api/pith-number/MIZYZMEN5H356CDAKKQCTWF4YC/graph.json","fetch_events":"https://pith.science/api/pith-number/MIZYZMEN5H356CDAKKQCTWF4YC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC/action/storage_attestation","attest_author":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC/action/author_attestation","sign_citation":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC/action/citation_signature","submit_replication":"https://pith.science/pith/MIZYZMEN5H356CDAKKQCTWF4YC/action/replication_record"}},"created_at":"2026-07-05T07:53:02.756404+00:00","updated_at":"2026-07-05T07:53:02.756404+00:00"}