{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:65EDA26VJARGW2FQ6OI6CNJT45","short_pith_number":"pith:65EDA26V","schema_version":"1.0","canonical_sha256":"f748306bd548226b68b0f391e13533e743383d6043f60861da1a8f2f0b6e8f15","source":{"kind":"arxiv","id":"2406.06393","version":2},"attestation_state":"computed","paper":{"title":"STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.GN"],"primary_cat":"cs.CV","authors_text":"Didong Li, Jiawen Chen, Jinwei Zhang, Muqing Zhou, Wenrong Wu, Yun Li","submitted_at":"2024-06-10T15:48:07Z","abstract_excerpt":"Recent advances in multi-modal algorithms have driven and been driven by the increasing availability of large image-text datasets, leading to significant strides in various fields, including computational pathology. However, in most existing medical image-text datasets, the text typically provides high-level summaries that may not sufficiently describe sub-tile regions within a large pathology image. For example, an image might cover an extensive tissue area containing cancerous and healthy regions, but the accompanying text might only specify that this image is a cancer slide, lacking the nua"},"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":"2406.06393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T15:48:07Z","cross_cats_sorted":["cs.CL","q-bio.GN"],"title_canon_sha256":"ec597ecdd797adcc26925ace3e2adac2f82f611bfeccbd2325c50cf367d9b881","abstract_canon_sha256":"586931242e31dc8ac3cf61568e9a62aa68297c07ff39692aa2a9a27bb3f61739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:48.377428Z","signature_b64":"zyfFfLN2TmjnxihBb0+zXHi9jbWY1gKuP1cLLJVCLJXA0VfP7lA97dVlBPWv6p5VCJKZkMylJqfJ/BwcVdqLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f748306bd548226b68b0f391e13533e743383d6043f60861da1a8f2f0b6e8f15","last_reissued_at":"2026-07-05T08:34:48.376950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:48.376950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.GN"],"primary_cat":"cs.CV","authors_text":"Didong Li, Jiawen Chen, Jinwei Zhang, Muqing Zhou, Wenrong Wu, Yun Li","submitted_at":"2024-06-10T15:48:07Z","abstract_excerpt":"Recent advances in multi-modal algorithms have driven and been driven by the increasing availability of large image-text datasets, leading to significant strides in various fields, including computational pathology. However, in most existing medical image-text datasets, the text typically provides high-level summaries that may not sufficiently describe sub-tile regions within a large pathology image. For example, an image might cover an extensive tissue area containing cancerous and healthy regions, but the accompanying text might only specify that this image is a cancer slide, lacking the nua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06393","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/2406.06393/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":"2406.06393","created_at":"2026-07-05T08:34:48.377003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06393v2","created_at":"2026-07-05T08:34:48.377003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06393","created_at":"2026-07-05T08:34:48.377003+00:00"},{"alias_kind":"pith_short_12","alias_value":"65EDA26VJARG","created_at":"2026-07-05T08:34:48.377003+00:00"},{"alias_kind":"pith_short_16","alias_value":"65EDA26VJARGW2FQ","created_at":"2026-07-05T08:34:48.377003+00:00"},{"alias_kind":"pith_short_8","alias_value":"65EDA26V","created_at":"2026-07-05T08:34:48.377003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"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":185,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45","json":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45.json","graph_json":"https://pith.science/api/pith-number/65EDA26VJARGW2FQ6OI6CNJT45/graph.json","events_json":"https://pith.science/api/pith-number/65EDA26VJARGW2FQ6OI6CNJT45/events.json","paper":"https://pith.science/paper/65EDA26V"},"agent_actions":{"view_html":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45","download_json":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45.json","view_paper":"https://pith.science/paper/65EDA26V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06393&json=true","fetch_graph":"https://pith.science/api/pith-number/65EDA26VJARGW2FQ6OI6CNJT45/graph.json","fetch_events":"https://pith.science/api/pith-number/65EDA26VJARGW2FQ6OI6CNJT45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45/action/storage_attestation","attest_author":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45/action/author_attestation","sign_citation":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45/action/citation_signature","submit_replication":"https://pith.science/pith/65EDA26VJARGW2FQ6OI6CNJT45/action/replication_record"}},"created_at":"2026-07-05T08:34:48.377003+00:00","updated_at":"2026-07-05T08:34:48.377003+00:00"}