{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:63XPPR2LQWRDPOOBF7CW53FSUK","short_pith_number":"pith:63XPPR2L","schema_version":"1.0","canonical_sha256":"f6eef7c74b85a237b9c12fc56eecb2a2abd8afdba7f79bbf2b6092b5e0690f02","source":{"kind":"arxiv","id":"2505.12120","version":1},"attestation_state":"computed","paper":{"title":"HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alexey Pchelnikov, Dmitry Nechaev, Ekaterina Ivanova","submitted_at":"2025-05-17T18:59:32Z","abstract_excerpt":"Recent advancements in Digital Pathology (DP), particularly through artificial intelligence and Foundation Models, have underscored the importance of large-scale, diverse, and richly annotated datasets. Despite their critical role, publicly available Whole Slide Image (WSI) datasets often lack sufficient scale, tissue diversity, and comprehensive clinical metadata, limiting the robustness and generalizability of AI models. In response, we introduce the HISTAI dataset, a large, multimodal, open-access WSI collection comprising over 60,000 slides from various tissue types. Each case in the HISTA"},"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":"2505.12120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-17T18:59:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ed58c43dac96fbcbcf2b3eece725d2d64f415befc098d866aba3c28facafb660","abstract_canon_sha256":"172d42545566fc059944369059931b82dc2006551623131143d4057dc4dae27d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:58.801946Z","signature_b64":"nAFhRjwnavJnpF/JwMcQPuA49Ct+hmrNC0kkRMF8V47+kHZyha/yyG2KB8eYBD4jyjZY1832NO7eKTYjJ1DPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6eef7c74b85a237b9c12fc56eecb2a2abd8afdba7f79bbf2b6092b5e0690f02","last_reissued_at":"2026-07-05T11:04:58.801508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:58.801508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alexey Pchelnikov, Dmitry Nechaev, Ekaterina Ivanova","submitted_at":"2025-05-17T18:59:32Z","abstract_excerpt":"Recent advancements in Digital Pathology (DP), particularly through artificial intelligence and Foundation Models, have underscored the importance of large-scale, diverse, and richly annotated datasets. Despite their critical role, publicly available Whole Slide Image (WSI) datasets often lack sufficient scale, tissue diversity, and comprehensive clinical metadata, limiting the robustness and generalizability of AI models. In response, we introduce the HISTAI dataset, a large, multimodal, open-access WSI collection comprising over 60,000 slides from various tissue types. Each case in the HISTA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12120","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/2505.12120/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":"2505.12120","created_at":"2026-07-05T11:04:58.801573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12120v1","created_at":"2026-07-05T11:04:58.801573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12120","created_at":"2026-07-05T11:04:58.801573+00:00"},{"alias_kind":"pith_short_12","alias_value":"63XPPR2LQWRD","created_at":"2026-07-05T11:04:58.801573+00:00"},{"alias_kind":"pith_short_16","alias_value":"63XPPR2LQWRDPOOB","created_at":"2026-07-05T11:04:58.801573+00:00"},{"alias_kind":"pith_short_8","alias_value":"63XPPR2L","created_at":"2026-07-05T11:04:58.801573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06983","citing_title":"DaX: Learning General Pathology Representations Across Scales","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04792","citing_title":"A Pathology Foundation Model for Gastric Cancer with Real-World Validation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25878","citing_title":"A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation","ref_index":54,"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":17,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03635","citing_title":"A Generative Foundation Model for Multimodal Histopathology","ref_index":62,"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":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08207","citing_title":"A Breast Vision Pathology Foundation Model for Real-world Clinical Utility","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK","json":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK.json","graph_json":"https://pith.science/api/pith-number/63XPPR2LQWRDPOOBF7CW53FSUK/graph.json","events_json":"https://pith.science/api/pith-number/63XPPR2LQWRDPOOBF7CW53FSUK/events.json","paper":"https://pith.science/paper/63XPPR2L"},"agent_actions":{"view_html":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK","download_json":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK.json","view_paper":"https://pith.science/paper/63XPPR2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12120&json=true","fetch_graph":"https://pith.science/api/pith-number/63XPPR2LQWRDPOOBF7CW53FSUK/graph.json","fetch_events":"https://pith.science/api/pith-number/63XPPR2LQWRDPOOBF7CW53FSUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK/action/storage_attestation","attest_author":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK/action/author_attestation","sign_citation":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK/action/citation_signature","submit_replication":"https://pith.science/pith/63XPPR2LQWRDPOOBF7CW53FSUK/action/replication_record"}},"created_at":"2026-07-05T11:04:58.801573+00:00","updated_at":"2026-07-05T11:04:58.801573+00:00"}