{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOEPVTU4FQT2PCTO2N647DRGEY","short_pith_number":"pith:XOEPVTU4","schema_version":"1.0","canonical_sha256":"bb88face9c2c27a78a6ed37dcf8e262611d87ec35ab1915d07e4701eafa2410f","source":{"kind":"arxiv","id":"2405.10254","version":2},"attestation_state":"computed","paper":{"title":"PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Adam Casson, Christopher Kanan, David Klimstra, Eric Zimmermann, Eugene Vorontsov, George Shaikovski, Gerard Oakley, James Hall, Jeremy D. Kunz, Juan A. Retamero, Julian Viret, Kristen Severson, Matthew Hanna, Michal Zelechowski, Neil Tenenholtz, Nicolo Fusi, Peter Hamilton, Razik Yousfi, Siqi Liu, Thomas J. Fuchs, William A. Moye, Yi Kan Wang","submitted_at":"2024-05-16T16:59:12Z","abstract_excerpt":"Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation"},"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":"2405.10254","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2024-05-16T16:59:12Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"cf6326c3867a1d40332f00db467459c511305647786e6701f05efc4b6784cc4f","abstract_canon_sha256":"f3ec66f8c7e3b6f4a5112ba266f697f97d020fc5a6378c0ccdf6cad311422e58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:55.149136Z","signature_b64":"SGECTzKnbg6pDC27vTgeNwxAIjs5hxLn2M5fMoy6Zs22xXsPGg8daBYHRQ1qvMPLx2fFdyuu8nvt0yejdFdUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb88face9c2c27a78a6ed37dcf8e262611d87ec35ab1915d07e4701eafa2410f","last_reissued_at":"2026-07-05T08:21:55.148654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:55.148654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Adam Casson, Christopher Kanan, David Klimstra, Eric Zimmermann, Eugene Vorontsov, George Shaikovski, Gerard Oakley, James Hall, Jeremy D. Kunz, Juan A. Retamero, Julian Viret, Kristen Severson, Matthew Hanna, Michal Zelechowski, Neil Tenenholtz, Nicolo Fusi, Peter Hamilton, Razik Yousfi, Siqi Liu, Thomas J. Fuchs, William A. Moye, Yi Kan Wang","submitted_at":"2024-05-16T16:59:12Z","abstract_excerpt":"Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10254","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.10254/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":"2405.10254","created_at":"2026-07-05T08:21:55.148712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10254v2","created_at":"2026-07-05T08:21:55.148712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10254","created_at":"2026-07-05T08:21:55.148712+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOEPVTU4FQT2","created_at":"2026-07-05T08:21:55.148712+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOEPVTU4FQT2PCTO","created_at":"2026-07-05T08:21:55.148712+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOEPVTU4","created_at":"2026-07-05T08:21:55.148712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17115","citing_title":"Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysis","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12407","citing_title":"How Seemingly Inconsequential Design Choices Dictate Performance of LLMs in Pathology","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12126","citing_title":"AGE-MIL: Anchor-Guided Evidence Learning for Patient-Level Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19491","citing_title":"Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning","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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30020","citing_title":"Uncertainty Estimation in Pathology Foundation Models via Deep Mutual Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29980","citing_title":"Genetically Aligned Patient Representations Improve Hematological Diagnosis","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30716","citing_title":"Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19491","citing_title":"Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09028","citing_title":"From Classical Machine Learning to Emerging Foundation Models: Review on Multimodal Data Integration for Cancer Research","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17326","citing_title":"Democratising Pathology Co-Pilots: An Open Pipeline and Dataset for Whole-Slide Vision-Language Modelling","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00902","citing_title":"Validation of Whole-Slide Foundation Models for Image Retrieval in TCGA Data","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY","json":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY.json","graph_json":"https://pith.science/api/pith-number/XOEPVTU4FQT2PCTO2N647DRGEY/graph.json","events_json":"https://pith.science/api/pith-number/XOEPVTU4FQT2PCTO2N647DRGEY/events.json","paper":"https://pith.science/paper/XOEPVTU4"},"agent_actions":{"view_html":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY","download_json":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY.json","view_paper":"https://pith.science/paper/XOEPVTU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10254&json=true","fetch_graph":"https://pith.science/api/pith-number/XOEPVTU4FQT2PCTO2N647DRGEY/graph.json","fetch_events":"https://pith.science/api/pith-number/XOEPVTU4FQT2PCTO2N647DRGEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY/action/storage_attestation","attest_author":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY/action/author_attestation","sign_citation":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY/action/citation_signature","submit_replication":"https://pith.science/pith/XOEPVTU4FQT2PCTO2N647DRGEY/action/replication_record"}},"created_at":"2026-07-05T08:21:55.148712+00:00","updated_at":"2026-07-05T08:21:55.148712+00:00"}