{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B5URHADKCCDNC77OZC4H2BJDQE","short_pith_number":"pith:B5URHADK","schema_version":"1.0","canonical_sha256":"0f6913806a1086d17feec8b87d0523811d85ae806aff111b1292286944039240","source":{"kind":"arxiv","id":"2501.02922","version":1},"attestation_state":"computed","paper":{"title":"Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christian F. Baumgartner, Cl\\'ement Grisi, Dominique van Midden, Fr\\'ed\\'erique Meeuwsen, Geert Litjens, Leslie Tessier, Susu Sun","submitted_at":"2025-01-06T11:03:04Z","abstract_excerpt":"Multiple Instance Learning (MIL) methods allow for gigapixel Whole-Slide Image (WSI) analysis with only slide-level annotations. Interpretability is crucial for safely deploying such algorithms in high-stakes medical domains. Traditional MIL methods offer explanations by highlighting salient regions. However, such spatial heatmaps provide limited insights for end users. To address this, we propose a novel inherently interpretable WSI-classification approach that uses human-understandable pathology concepts to generate explanations. Our proposed Concept MIL model leverages recent advances in vi"},"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":"2501.02922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T11:03:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22516879dd8c1975e19bae064cc6d05989607b958a9ed3cbd24788e3d7bd4c21","abstract_canon_sha256":"dbf9658918542fea4ee9fb37438f535c31ce9cc38dad76efeac26f17ab91bbb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:27.072209Z","signature_b64":"0/XUXcyEkIOH9/jBE5K9O3Wd26vFaI1CkR/POf/Bdx71wbua8CNXk7We6ZXLt+gJhnciPC7IFwGki7sHw25MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f6913806a1086d17feec8b87d0523811d85ae806aff111b1292286944039240","last_reissued_at":"2026-07-05T09:57:27.071629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:27.071629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christian F. Baumgartner, Cl\\'ement Grisi, Dominique van Midden, Fr\\'ed\\'erique Meeuwsen, Geert Litjens, Leslie Tessier, Susu Sun","submitted_at":"2025-01-06T11:03:04Z","abstract_excerpt":"Multiple Instance Learning (MIL) methods allow for gigapixel Whole-Slide Image (WSI) analysis with only slide-level annotations. Interpretability is crucial for safely deploying such algorithms in high-stakes medical domains. Traditional MIL methods offer explanations by highlighting salient regions. However, such spatial heatmaps provide limited insights for end users. To address this, we propose a novel inherently interpretable WSI-classification approach that uses human-understandable pathology concepts to generate explanations. Our proposed Concept MIL model leverages recent advances in vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02922","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/2501.02922/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":"2501.02922","created_at":"2026-07-05T09:57:27.071704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02922v1","created_at":"2026-07-05T09:57:27.071704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02922","created_at":"2026-07-05T09:57:27.071704+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5URHADKCCDN","created_at":"2026-07-05T09:57:27.071704+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5URHADKCCDNC77O","created_at":"2026-07-05T09:57:27.071704+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5URHADK","created_at":"2026-07-05T09:57:27.071704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06224","citing_title":"Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE","json":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE.json","graph_json":"https://pith.science/api/pith-number/B5URHADKCCDNC77OZC4H2BJDQE/graph.json","events_json":"https://pith.science/api/pith-number/B5URHADKCCDNC77OZC4H2BJDQE/events.json","paper":"https://pith.science/paper/B5URHADK"},"agent_actions":{"view_html":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE","download_json":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE.json","view_paper":"https://pith.science/paper/B5URHADK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02922&json=true","fetch_graph":"https://pith.science/api/pith-number/B5URHADKCCDNC77OZC4H2BJDQE/graph.json","fetch_events":"https://pith.science/api/pith-number/B5URHADKCCDNC77OZC4H2BJDQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE/action/storage_attestation","attest_author":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE/action/author_attestation","sign_citation":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE/action/citation_signature","submit_replication":"https://pith.science/pith/B5URHADKCCDNC77OZC4H2BJDQE/action/replication_record"}},"created_at":"2026-07-05T09:57:27.071704+00:00","updated_at":"2026-07-05T09:57:27.071704+00:00"}