{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JU573NO6CA2OVBD2G5IZVYUJFZ","short_pith_number":"pith:JU573NO6","schema_version":"1.0","canonical_sha256":"4d3bfdb5de1034ea847a37519ae2892e64dacf1989b80919ad35df6c8656e854","source":{"kind":"arxiv","id":"2206.08885","version":2},"attestation_state":"computed","paper":{"title":"Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ME"],"primary_cat":"eess.IV","authors_text":"Andrew H. Song, Drew F.K. Williamson, Faisal Mahmood, Iain Carmichael, Richard J. Chen, Tiffany Y. Chen","submitted_at":"2022-06-17T16:35:35Z","abstract_excerpt":"Supervised learning tasks such as cancer survival prediction from gigapixel whole slide images (WSIs) are a critical challenge in computational pathology that requires modeling complex features of the tumor microenvironment. These learning tasks are often solved with deep multi-instance learning (MIL) models that do not explicitly capture intratumoral heterogeneity. We develop a novel variance pooling architecture that enables a MIL model to incorporate intratumoral heterogeneity into its predictions. Two interpretability tools based on representative patches are illustrated to probe the biolo"},"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":"2206.08885","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2022-06-17T16:35:35Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ME"],"title_canon_sha256":"ae1c0cabe20385ca32c280616c8847817055030863f3fa465d50de0a1e67ca1e","abstract_canon_sha256":"1450a90eab54df1ba81091216484e51a0c759f777c74e550e20eec0ae0920edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:27.245860Z","signature_b64":"56PlQvyQSpmRfutj7fnkXr2aDD6peKFk3ngaPh/mX89Wz4OxC3qWIZbgGfORyXTa8oRBhscUDd7Q/5zM/PzcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d3bfdb5de1034ea847a37519ae2892e64dacf1989b80919ad35df6c8656e854","last_reissued_at":"2026-07-05T05:17:27.245353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:27.245353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ME"],"primary_cat":"eess.IV","authors_text":"Andrew H. Song, Drew F.K. Williamson, Faisal Mahmood, Iain Carmichael, Richard J. Chen, Tiffany Y. Chen","submitted_at":"2022-06-17T16:35:35Z","abstract_excerpt":"Supervised learning tasks such as cancer survival prediction from gigapixel whole slide images (WSIs) are a critical challenge in computational pathology that requires modeling complex features of the tumor microenvironment. These learning tasks are often solved with deep multi-instance learning (MIL) models that do not explicitly capture intratumoral heterogeneity. We develop a novel variance pooling architecture that enables a MIL model to incorporate intratumoral heterogeneity into its predictions. Two interpretability tools based on representative patches are illustrated to probe the biolo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08885","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/2206.08885/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":"2206.08885","created_at":"2026-07-05T05:17:27.245419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08885v2","created_at":"2026-07-05T05:17:27.245419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08885","created_at":"2026-07-05T05:17:27.245419+00:00"},{"alias_kind":"pith_short_12","alias_value":"JU573NO6CA2O","created_at":"2026-07-05T05:17:27.245419+00:00"},{"alias_kind":"pith_short_16","alias_value":"JU573NO6CA2OVBD2","created_at":"2026-07-05T05:17:27.245419+00:00"},{"alias_kind":"pith_short_8","alias_value":"JU573NO6","created_at":"2026-07-05T05:17:27.245419+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/JU573NO6CA2OVBD2G5IZVYUJFZ","json":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ.json","graph_json":"https://pith.science/api/pith-number/JU573NO6CA2OVBD2G5IZVYUJFZ/graph.json","events_json":"https://pith.science/api/pith-number/JU573NO6CA2OVBD2G5IZVYUJFZ/events.json","paper":"https://pith.science/paper/JU573NO6"},"agent_actions":{"view_html":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ","download_json":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ.json","view_paper":"https://pith.science/paper/JU573NO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08885&json=true","fetch_graph":"https://pith.science/api/pith-number/JU573NO6CA2OVBD2G5IZVYUJFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JU573NO6CA2OVBD2G5IZVYUJFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ/action/storage_attestation","attest_author":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ/action/author_attestation","sign_citation":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ/action/citation_signature","submit_replication":"https://pith.science/pith/JU573NO6CA2OVBD2G5IZVYUJFZ/action/replication_record"}},"created_at":"2026-07-05T05:17:27.245419+00:00","updated_at":"2026-07-05T05:17:27.245419+00:00"}