{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4YAKZJD5UHVJ25YVP3DITFOF2A","short_pith_number":"pith:4YAKZJD5","schema_version":"1.0","canonical_sha256":"e600aca47da1ea9d77157ec68995c5d00b88635cf4f699b925e1295df9aec129","source":{"kind":"arxiv","id":"2408.00738","version":3},"attestation_state":"computed","paper":{"title":"Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Casson, David Klimstra, Eric Zimmermann, Eugene Vorontsov, George Shaikovski, James Hall, Julian Viret, Kristen Severson, Michal Zelechowski, Neil Tenenholtz, Nicolo Fusi, Razik Yousfi, Siqi Liu, Thomas Fuchs","submitted_at":"2024-08-01T17:35:58Z","abstract_excerpt":"Foundation models are rapidly being developed for computational pathology applications. However, it remains an open question which factors are most important for downstream performance with data scale and diversity, model size, and training algorithm all playing a role. In this work, we propose algorithmic modifications, tailored for pathology, and we present the result of scaling both data and model size, surpassing previous studies in both dimensions. We introduce three new models: Virchow2, a 632 million parameter vision transformer, Virchow2G, a 1.9 billion parameter vision transformer, an"},"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":"2408.00738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"b734d4d202e499d0f3794e59108eb19e4c6b1ba386912d9009349fe419d0e64f","abstract_canon_sha256":"e43b74d8a99c35a690723f85e1ab7193759aa33735bc6f19671bec00d68f2df2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:47.831930Z","signature_b64":"amvFzQ/nY0K5bCHijRTvoizqyPAKoYiBdsV/kOwAuGiJm9Zlfh7QHwWi6aLRh2pEcpNB7llafZc9dwnqBSXuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e600aca47da1ea9d77157ec68995c5d00b88635cf4f699b925e1295df9aec129","last_reissued_at":"2026-07-05T09:31:47.831445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:47.831445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Casson, David Klimstra, Eric Zimmermann, Eugene Vorontsov, George Shaikovski, James Hall, Julian Viret, Kristen Severson, Michal Zelechowski, Neil Tenenholtz, Nicolo Fusi, Razik Yousfi, Siqi Liu, Thomas Fuchs","submitted_at":"2024-08-01T17:35:58Z","abstract_excerpt":"Foundation models are rapidly being developed for computational pathology applications. However, it remains an open question which factors are most important for downstream performance with data scale and diversity, model size, and training algorithm all playing a role. In this work, we propose algorithmic modifications, tailored for pathology, and we present the result of scaling both data and model size, surpassing previous studies in both dimensions. We introduce three new models: Virchow2, a 632 million parameter vision transformer, Virchow2G, a 1.9 billion parameter vision transformer, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00738","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/2408.00738/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":"2408.00738","created_at":"2026-07-05T09:31:47.831499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00738v3","created_at":"2026-07-05T09:31:47.831499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00738","created_at":"2026-07-05T09:31:47.831499+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YAKZJD5UHVJ","created_at":"2026-07-05T09:31:47.831499+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YAKZJD5UHVJ25YV","created_at":"2026-07-05T09:31:47.831499+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YAKZJD5","created_at":"2026-07-05T09:31:47.831499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08093","citing_title":"A Multi-modal Agentic Co-pilot for Evidence Grounded Computational Pathology","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06983","citing_title":"DaX: Learning General Pathology Representations Across Scales","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07368","citing_title":"Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07036","citing_title":"STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06867","citing_title":"Multi-FRuGaL: Multimodal Flexible Redundancy-aware Decomposed Gated Learning for Cancer Diagnosis and Prognosis","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06864","citing_title":"LRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image Classification","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06224","citing_title":"Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04792","citing_title":"A Pathology Foundation Model for Gastric Cancer with Real-World Validation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04764","citing_title":"Do Foundation Models See Biology? Evaluating Attention Coherence with Spatial Transcriptomics in Glioblastoma","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00802","citing_title":"CellPrior-Net: Prior-Guided Nuclei Detection and Classification for H&E Whole-Slide Images","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24253","citing_title":"CRISP -- Clustering-Based Redundancy-Reduced Instance Sampling for Pathology Case Representation and Retrieval","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28697","citing_title":"Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30020","citing_title":"Uncertainty Estimation in Pathology Foundation Models via Deep Mutual Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28395","citing_title":"JASPR: Joint Spatial Representation learning of histology and spatial genomics for improved virtual genomic screening and clinical prognostication","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25878","citing_title":"A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07590","citing_title":"SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03644","citing_title":"Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06723","citing_title":"Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shifts","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11344","citing_title":"MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expression","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20402","citing_title":"Transformer-Based Hematological Malignancy Prediction from Peripheral Blood Smears in a Real-World Cohort","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22347","citing_title":"Enabling clinical use of foundation models for computational pathology","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03635","citing_title":"A Generative Foundation Model for Multimodal Histopathology","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08276","citing_title":"Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24679","citing_title":"Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23706","citing_title":"Weakly Supervised Multicenter Nancy Index Scoring in Ulcerative Colitis Using Foundation Models","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A","json":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A.json","graph_json":"https://pith.science/api/pith-number/4YAKZJD5UHVJ25YVP3DITFOF2A/graph.json","events_json":"https://pith.science/api/pith-number/4YAKZJD5UHVJ25YVP3DITFOF2A/events.json","paper":"https://pith.science/paper/4YAKZJD5"},"agent_actions":{"view_html":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A","download_json":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A.json","view_paper":"https://pith.science/paper/4YAKZJD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00738&json=true","fetch_graph":"https://pith.science/api/pith-number/4YAKZJD5UHVJ25YVP3DITFOF2A/graph.json","fetch_events":"https://pith.science/api/pith-number/4YAKZJD5UHVJ25YVP3DITFOF2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A/action/storage_attestation","attest_author":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A/action/author_attestation","sign_citation":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A/action/citation_signature","submit_replication":"https://pith.science/pith/4YAKZJD5UHVJ25YVP3DITFOF2A/action/replication_record"}},"created_at":"2026-07-05T09:31:47.831499+00:00","updated_at":"2026-07-05T09:31:47.831499+00:00"}