{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XAMBB3B2ODDH366LYNXW754ZME","short_pith_number":"pith:XAMBB3B2","schema_version":"1.0","canonical_sha256":"b81810ec3a70c67dfbcbc36f6ff7996137626544124e558ab2c3af554cb00451","source":{"kind":"arxiv","id":"1909.11575","version":2},"attestation_state":"computed","paper":{"title":"A Closer Look at Domain Shift for Deep Learning in Histopathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Claes Lundstr\\\"om, Gabriel Eilertsen, Jonas Unger, Karin Stacke","submitted_at":"2019-09-25T16:06:05Z","abstract_excerpt":"Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images. We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to. Most centrally, we present a novel measure fo"},"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":"1909.11575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-25T16:06:05Z","cross_cats_sorted":[],"title_canon_sha256":"e0efdf174a02aa2c2125454a0376d1aab6d381363cc5b0af9a6c34b73287ab51","abstract_canon_sha256":"b29496bd89a14db7bcf05656b87842abb4bcdd822f4da33a4411efd7dc44b6d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:26.688133Z","signature_b64":"NdANbg/swaIjYkTI5LlQbVwIbt+LPp70u0Mvql4A9YgOd7PYtu/5QA2mBQZLmXbeEeww5PNpP+GZUQRyTC8cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b81810ec3a70c67dfbcbc36f6ff7996137626544124e558ab2c3af554cb00451","last_reissued_at":"2026-07-05T00:07:26.687653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:26.687653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at Domain Shift for Deep Learning in Histopathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Claes Lundstr\\\"om, Gabriel Eilertsen, Jonas Unger, Karin Stacke","submitted_at":"2019-09-25T16:06:05Z","abstract_excerpt":"Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images. We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to. Most centrally, we present a novel measure fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11575","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/1909.11575/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":"1909.11575","created_at":"2026-07-05T00:07:26.687720+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11575v2","created_at":"2026-07-05T00:07:26.687720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11575","created_at":"2026-07-05T00:07:26.687720+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAMBB3B2ODDH","created_at":"2026-07-05T00:07:26.687720+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAMBB3B2ODDH366L","created_at":"2026-07-05T00:07:26.687720+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAMBB3B2","created_at":"2026-07-05T00:07:26.687720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.22347","citing_title":"Enabling clinical use of foundation models for computational pathology","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25817","citing_title":"Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME","json":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME.json","graph_json":"https://pith.science/api/pith-number/XAMBB3B2ODDH366LYNXW754ZME/graph.json","events_json":"https://pith.science/api/pith-number/XAMBB3B2ODDH366LYNXW754ZME/events.json","paper":"https://pith.science/paper/XAMBB3B2"},"agent_actions":{"view_html":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME","download_json":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME.json","view_paper":"https://pith.science/paper/XAMBB3B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11575&json=true","fetch_graph":"https://pith.science/api/pith-number/XAMBB3B2ODDH366LYNXW754ZME/graph.json","fetch_events":"https://pith.science/api/pith-number/XAMBB3B2ODDH366LYNXW754ZME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME/action/storage_attestation","attest_author":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME/action/author_attestation","sign_citation":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME/action/citation_signature","submit_replication":"https://pith.science/pith/XAMBB3B2ODDH366LYNXW754ZME/action/replication_record"}},"created_at":"2026-07-05T00:07:26.687720+00:00","updated_at":"2026-07-05T00:07:26.687720+00:00"}