{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NE5SSDY64FMTCTYSGK3MWCTCYC","short_pith_number":"pith:NE5SSDY6","schema_version":"1.0","canonical_sha256":"693b290f1ee159314f1232b6cb0a62c092506b562fcd790e452e8ff89d074697","source":{"kind":"arxiv","id":"1904.03127","version":2},"attestation_state":"computed","paper":{"title":"Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Katja Steiger, Magdalini Paschali, Martin Mollenhauer, Muhammad Ferjad Naeem, Nassir Navab, Walter Simson","submitted_at":"2019-04-05T15:41:12Z","abstract_excerpt":"In this paper, we propose a novel interpretation method tailored to histological Whole Slide Image (WSI) processing. A Deep Neural Network (DNN), inspired by Bag-of-Features models is equipped with a Multiple Instance Learning (MIL) branch and trained with weak supervision for WSI classification. MIL avoids label ambiguity and enhances our model's expressive power without guiding its attention. We utilize a fine-grained logit heatmap of the models activations to interpret its decision-making process. The proposed method is quantitatively and qualitatively evaluated on two challenging histology"},"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":"1904.03127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-05T15:41:12Z","cross_cats_sorted":[],"title_canon_sha256":"b14ac2829c8af558967f3da6a570ca6875595f1314f05cdb0269359c573908e8","abstract_canon_sha256":"385055303f1a82089f5403b25e59c50b0e493f62961238d9adaf863760ed84d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:29.516718Z","signature_b64":"QVfY8t2qvuc+7XUNkEeHpMmQV01zrzuqfkTMmqdx3fap5RCgGxGO9cnZcopfcpZ5mLbLvTZ/4ZTzYTZIMQiLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"693b290f1ee159314f1232b6cb0a62c092506b562fcd790e452e8ff89d074697","last_reissued_at":"2026-05-17T23:48:29.516015Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:29.516015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Katja Steiger, Magdalini Paschali, Martin Mollenhauer, Muhammad Ferjad Naeem, Nassir Navab, Walter Simson","submitted_at":"2019-04-05T15:41:12Z","abstract_excerpt":"In this paper, we propose a novel interpretation method tailored to histological Whole Slide Image (WSI) processing. A Deep Neural Network (DNN), inspired by Bag-of-Features models is equipped with a Multiple Instance Learning (MIL) branch and trained with weak supervision for WSI classification. MIL avoids label ambiguity and enhances our model's expressive power without guiding its attention. We utilize a fine-grained logit heatmap of the models activations to interpret its decision-making process. The proposed method is quantitatively and qualitatively evaluated on two challenging histology"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03127","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":""},"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":"1904.03127","created_at":"2026-05-17T23:48:29.516143+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03127v2","created_at":"2026-05-17T23:48:29.516143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03127","created_at":"2026-05-17T23:48:29.516143+00:00"},{"alias_kind":"pith_short_12","alias_value":"NE5SSDY64FMT","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NE5SSDY64FMTCTYS","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NE5SSDY6","created_at":"2026-05-18T12:33:24.271573+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/NE5SSDY64FMTCTYSGK3MWCTCYC","json":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC.json","graph_json":"https://pith.science/api/pith-number/NE5SSDY64FMTCTYSGK3MWCTCYC/graph.json","events_json":"https://pith.science/api/pith-number/NE5SSDY64FMTCTYSGK3MWCTCYC/events.json","paper":"https://pith.science/paper/NE5SSDY6"},"agent_actions":{"view_html":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC","download_json":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC.json","view_paper":"https://pith.science/paper/NE5SSDY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03127&json=true","fetch_graph":"https://pith.science/api/pith-number/NE5SSDY64FMTCTYSGK3MWCTCYC/graph.json","fetch_events":"https://pith.science/api/pith-number/NE5SSDY64FMTCTYSGK3MWCTCYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC/action/storage_attestation","attest_author":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC/action/author_attestation","sign_citation":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC/action/citation_signature","submit_replication":"https://pith.science/pith/NE5SSDY64FMTCTYSGK3MWCTCYC/action/replication_record"}},"created_at":"2026-05-17T23:48:29.516143+00:00","updated_at":"2026-05-17T23:48:29.516143+00:00"}