{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FS2F3QVDP3YABXONNFGYAFQDVJ","short_pith_number":"pith:FS2F3QVD","schema_version":"1.0","canonical_sha256":"2cb45dc2a37ef000ddcd694d801603aa6ac752fbe74c15fd29c744da19c0b908","source":{"kind":"arxiv","id":"2306.07831","version":1},"attestation_state":"computed","paper":{"title":"Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zhang, Bowen Chen, Drew F.K. Williamson, Faisal Mahmood, Long Phi Le, Ming Y. Lu, Richard J. Chen, Tong Ding, Yung-Sung Chuang","submitted_at":"2023-06-13T15:05:24Z","abstract_excerpt":"Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In "},"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":"2306.07831","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T15:05:24Z","cross_cats_sorted":[],"title_canon_sha256":"e29a1a4fc652da3592949fa2915002866391830e0669fb3427832c934ae523c4","abstract_canon_sha256":"d818e64a2ae21529bb54625d2c272a8a7c337f13b5e04bd0da4b89834feb9897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:09.508396Z","signature_b64":"zjen4mfGxTbJTAbvNb3KXyNfMUX2B7rUa89NXYmU/yR4FlnSPywgcsq4m97cWUbxH2IG4saho9jjDrE8PjTKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb45dc2a37ef000ddcd694d801603aa6ac752fbe74c15fd29c744da19c0b908","last_reissued_at":"2026-07-05T06:20:09.507860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:09.507860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zhang, Bowen Chen, Drew F.K. Williamson, Faisal Mahmood, Long Phi Le, Ming Y. Lu, Richard J. Chen, Tong Ding, Yung-Sung Chuang","submitted_at":"2023-06-13T15:05:24Z","abstract_excerpt":"Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07831","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/2306.07831/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":"2306.07831","created_at":"2026-07-05T06:20:09.507934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07831v1","created_at":"2026-07-05T06:20:09.507934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07831","created_at":"2026-07-05T06:20:09.507934+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS2F3QVDP3YA","created_at":"2026-07-05T06:20:09.507934+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS2F3QVDP3YABXON","created_at":"2026-07-05T06:20:09.507934+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS2F3QVD","created_at":"2026-07-05T06:20:09.507934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08460","citing_title":"F3-Net: Foundation Model for Full Abnormality Segmentation of Medical Images with Flexible Input Modality Requirement","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ","json":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ.json","graph_json":"https://pith.science/api/pith-number/FS2F3QVDP3YABXONNFGYAFQDVJ/graph.json","events_json":"https://pith.science/api/pith-number/FS2F3QVDP3YABXONNFGYAFQDVJ/events.json","paper":"https://pith.science/paper/FS2F3QVD"},"agent_actions":{"view_html":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ","download_json":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ.json","view_paper":"https://pith.science/paper/FS2F3QVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07831&json=true","fetch_graph":"https://pith.science/api/pith-number/FS2F3QVDP3YABXONNFGYAFQDVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FS2F3QVDP3YABXONNFGYAFQDVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ/action/storage_attestation","attest_author":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ/action/author_attestation","sign_citation":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ/action/citation_signature","submit_replication":"https://pith.science/pith/FS2F3QVDP3YABXONNFGYAFQDVJ/action/replication_record"}},"created_at":"2026-07-05T06:20:09.507934+00:00","updated_at":"2026-07-05T06:20:09.507934+00:00"}