{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UJK63FRVSHPI6VLUOWSZG324GF","short_pith_number":"pith:UJK63FRV","schema_version":"1.0","canonical_sha256":"a255ed963591de8f557475a5936f5c3166cdb59d69a61f4fdd494fc56b15bf7c","source":{"kind":"arxiv","id":"2206.02647","version":1},"attestation_state":"computed","paper":{"title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew D. Trister, Chengkuan Chen, Faisal Mahmood, Rahul G. Krishnan, Richard J. Chen, Tiffany Y. Chen, Yicong Li","submitted_at":"2022-06-06T14:35:14Z","abstract_excerpt":"Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. - 256x256, 384384). For gigapixel whole-slide imaging (WSI) in computational pathology, WSIs can be as large as 150000x150000 pixels at 20X magnification and exhibit a hierarchical structure of visual tokens across varying resolutions: from 16x16 images capture spatial patterns among cells, to 4096x4096 images characterizing interactions within the tissue microenvironment. We introduce a new"},"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":"2206.02647","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-06T14:35:14Z","cross_cats_sorted":[],"title_canon_sha256":"61c6bbbe3cba04bdde68c803135eead0e0dc57936f2e42542311aa71105e5a52","abstract_canon_sha256":"13592d5e835ae9e7adea8ec00b211de8ae0c32e22d3d6bd76be0158b0bcd2cc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:19.895434Z","signature_b64":"AQsB2P3ueROY1mARh5hiUo3RefIIeyWeo2B3twZnkm6jgFApofnuaYPuWkxE3NBaE+YysHTmG1GCDGxzELOpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a255ed963591de8f557475a5936f5c3166cdb59d69a61f4fdd494fc56b15bf7c","last_reissued_at":"2026-07-05T04:29:19.895066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:19.895066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew D. Trister, Chengkuan Chen, Faisal Mahmood, Rahul G. Krishnan, Richard J. Chen, Tiffany Y. Chen, Yicong Li","submitted_at":"2022-06-06T14:35:14Z","abstract_excerpt":"Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. - 256x256, 384384). For gigapixel whole-slide imaging (WSI) in computational pathology, WSIs can be as large as 150000x150000 pixels at 20X magnification and exhibit a hierarchical structure of visual tokens across varying resolutions: from 16x16 images capture spatial patterns among cells, to 4096x4096 images characterizing interactions within the tissue microenvironment. We introduce a new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02647","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/2206.02647/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":"2206.02647","created_at":"2026-07-05T04:29:19.895124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02647v1","created_at":"2026-07-05T04:29:19.895124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02647","created_at":"2026-07-05T04:29:19.895124+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJK63FRVSHPI","created_at":"2026-07-05T04:29:19.895124+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJK63FRVSHPI6VLU","created_at":"2026-07-05T04:29:19.895124+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJK63FRV","created_at":"2026-07-05T04:29:19.895124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16886","citing_title":"Sparser2Sparse: Single-shot Sparser-to-Sparse Learning for Spatial Transcriptomics Imputation with Natural Image Co-learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF","json":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF.json","graph_json":"https://pith.science/api/pith-number/UJK63FRVSHPI6VLUOWSZG324GF/graph.json","events_json":"https://pith.science/api/pith-number/UJK63FRVSHPI6VLUOWSZG324GF/events.json","paper":"https://pith.science/paper/UJK63FRV"},"agent_actions":{"view_html":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF","download_json":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF.json","view_paper":"https://pith.science/paper/UJK63FRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02647&json=true","fetch_graph":"https://pith.science/api/pith-number/UJK63FRVSHPI6VLUOWSZG324GF/graph.json","fetch_events":"https://pith.science/api/pith-number/UJK63FRVSHPI6VLUOWSZG324GF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF/action/storage_attestation","attest_author":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF/action/author_attestation","sign_citation":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF/action/citation_signature","submit_replication":"https://pith.science/pith/UJK63FRVSHPI6VLUOWSZG324GF/action/replication_record"}},"created_at":"2026-07-05T04:29:19.895124+00:00","updated_at":"2026-07-05T04:29:19.895124+00:00"}