{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZDRVL2Z2TEVJOLNNOFIXJDC2AZ","short_pith_number":"pith:ZDRVL2Z2","schema_version":"1.0","canonical_sha256":"c8e355eb3a992a972dad7151748c5a064acc9df97452a94a653084560a46a232","source":{"kind":"arxiv","id":"2008.01478","version":3},"attestation_state":"computed","paper":{"title":"Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs To Improve Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Henning Muller, Mara Graziani, Sebastian Otalora, Stephane Marchand-Maillet, Vincent Andrearczyk","submitted_at":"2020-08-04T12:10:35Z","abstract_excerpt":"Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model. Building on top of successfully existing techniques such as multi-task learning, domain adversarial training and concept-based interpretability, this paper addresses the challenge of introducing diagnostic factors in the training objectives. Here we"},"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":"2008.01478","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-08-04T12:10:35Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"d7d310c5ad7699a9d1db3dc88d289ad7103b44a78103c94c937d0c586e49b59c","abstract_canon_sha256":"928f149da401aeb1f09a3ceaf536d98663987616197511844d438f367551ba08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:53.814112Z","signature_b64":"/KNLeTBX10xdGRttiqdq9e4lrorWHWB5JBe4bJjE5FfVuXKn/jH9tYFTiiY6y1/Q/aUYZkgALlgADBtCbKOFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e355eb3a992a972dad7151748c5a064acc9df97452a94a653084560a46a232","last_reissued_at":"2026-07-05T06:22:53.813742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:53.813742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs To Improve Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Henning Muller, Mara Graziani, Sebastian Otalora, Stephane Marchand-Maillet, Vincent Andrearczyk","submitted_at":"2020-08-04T12:10:35Z","abstract_excerpt":"Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model. Building on top of successfully existing techniques such as multi-task learning, domain adversarial training and concept-based interpretability, this paper addresses the challenge of introducing diagnostic factors in the training objectives. Here we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01478","kind":"arxiv","version":3},"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/2008.01478/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":"2008.01478","created_at":"2026-07-05T06:22:53.813806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.01478v3","created_at":"2026-07-05T06:22:53.813806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01478","created_at":"2026-07-05T06:22:53.813806+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDRVL2Z2TEVJ","created_at":"2026-07-05T06:22:53.813806+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDRVL2Z2TEVJOLNN","created_at":"2026-07-05T06:22:53.813806+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDRVL2Z2","created_at":"2026-07-05T06:22:53.813806+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/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ","json":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ.json","graph_json":"https://pith.science/api/pith-number/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/graph.json","events_json":"https://pith.science/api/pith-number/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/events.json","paper":"https://pith.science/paper/ZDRVL2Z2"},"agent_actions":{"view_html":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ","download_json":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ.json","view_paper":"https://pith.science/paper/ZDRVL2Z2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.01478&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZDRVL2Z2TEVJOLNNOFIXJDC2AZ/action/replication_record"}},"created_at":"2026-07-05T06:22:53.813806+00:00","updated_at":"2026-07-05T06:22:53.813806+00:00"}