{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E4ZDE2KG34VO2TBDDKHPDWHZ6H","short_pith_number":"pith:E4ZDE2KG","schema_version":"1.0","canonical_sha256":"2732326946df2aed4c231a8ef1d8f9f1c88acb3b0ea9ad52064ef51709b9b984","source":{"kind":"arxiv","id":"2402.17228","version":4},"attestation_state":"computed","paper":{"title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Liu, Fengtao Zhou, Sheng Huang, Wenhao Tang, Xiang Zhu, Yi Zhang","submitted_at":"2024-02-27T05:42:38Z","abstract_excerpt":"Multiple instance learning (MIL) is the most widely used framework in computational pathology, encompassing sub-typing, diagnosis, prognosis, and more. However, the existing MIL paradigm typically requires an offline instance feature extractor, such as a pre-trained ResNet or a foundation model. This approach lacks the capability for feature fine-tuning within the specific downstream tasks, limiting its adaptability and performance. To address this issue, we propose a Re-embedded Regional Transformer (R$^2$T) for re-embedding the instance features online, which captures fine-grained local feat"},"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":"2402.17228","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T05:42:38Z","cross_cats_sorted":[],"title_canon_sha256":"a23e9f300f39f2e6034dc4e6900d5dae8b63be53171b48e314ff2b0f70bfa60b","abstract_canon_sha256":"88e677cd4335a441f2e48ee5483cef35e3f61aacfb1339ced74100de4f24e08a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:12.704533Z","signature_b64":"RipIQ6kNQnjxWP13n+SLN5VyfK5ye60iE+Wn6xtf3szVQguSp1Gp8xMft/BfKszDPrlie0xzUihHy425OUQoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2732326946df2aed4c231a8ef1d8f9f1c88acb3b0ea9ad52064ef51709b9b984","last_reissued_at":"2026-07-05T08:48:12.704058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:12.704058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Liu, Fengtao Zhou, Sheng Huang, Wenhao Tang, Xiang Zhu, Yi Zhang","submitted_at":"2024-02-27T05:42:38Z","abstract_excerpt":"Multiple instance learning (MIL) is the most widely used framework in computational pathology, encompassing sub-typing, diagnosis, prognosis, and more. However, the existing MIL paradigm typically requires an offline instance feature extractor, such as a pre-trained ResNet or a foundation model. This approach lacks the capability for feature fine-tuning within the specific downstream tasks, limiting its adaptability and performance. To address this issue, we propose a Re-embedded Regional Transformer (R$^2$T) for re-embedding the instance features online, which captures fine-grained local feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17228","kind":"arxiv","version":4},"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/2402.17228/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":"2402.17228","created_at":"2026-07-05T08:48:12.704115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17228v4","created_at":"2026-07-05T08:48:12.704115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17228","created_at":"2026-07-05T08:48:12.704115+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4ZDE2KG34VO","created_at":"2026-07-05T08:48:12.704115+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4ZDE2KG34VO2TBD","created_at":"2026-07-05T08:48:12.704115+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4ZDE2KG","created_at":"2026-07-05T08:48:12.704115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09022","citing_title":"Do Multiple Instance Learning Models Transfer?","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H","json":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H.json","graph_json":"https://pith.science/api/pith-number/E4ZDE2KG34VO2TBDDKHPDWHZ6H/graph.json","events_json":"https://pith.science/api/pith-number/E4ZDE2KG34VO2TBDDKHPDWHZ6H/events.json","paper":"https://pith.science/paper/E4ZDE2KG"},"agent_actions":{"view_html":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H","download_json":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H.json","view_paper":"https://pith.science/paper/E4ZDE2KG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17228&json=true","fetch_graph":"https://pith.science/api/pith-number/E4ZDE2KG34VO2TBDDKHPDWHZ6H/graph.json","fetch_events":"https://pith.science/api/pith-number/E4ZDE2KG34VO2TBDDKHPDWHZ6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H/action/storage_attestation","attest_author":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H/action/author_attestation","sign_citation":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H/action/citation_signature","submit_replication":"https://pith.science/pith/E4ZDE2KG34VO2TBDDKHPDWHZ6H/action/replication_record"}},"created_at":"2026-07-05T08:48:12.704115+00:00","updated_at":"2026-07-05T08:48:12.704115+00:00"}