{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W5I2SSY76UFF6ZOIJG5VYKAHTD","short_pith_number":"pith:W5I2SSY7","schema_version":"1.0","canonical_sha256":"b751a94b1ff50a5f65c849bb5c280798c678b06ec2916848ed1a7d05a0ad54ef","source":{"kind":"arxiv","id":"2407.00203","version":1},"attestation_state":"computed","paper":{"title":"PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglu Zhu, Jingxiong Li, Kai Zhang, Lin Yang, Tao Lin, Xingheng Lyu, Yixuan Si, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui","submitted_at":"2024-06-28T19:18:09Z","abstract_excerpt":"Vision Language Models (VLMs) like CLIP have attracted substantial attention in pathology, serving as backbones for applications such as zero-shot image classification and Whole Slide Image (WSI) analysis. Additionally, they can function as vision encoders when combined with large language models (LLMs) to support broader capabilities. Current efforts to train pathology VLMs rely on pathology image-text pairs from platforms like PubMed, YouTube, and Twitter, which provide limited, unscalable data with generally suboptimal image quality. In this work, we leverage large-scale WSI datasets like T"},"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":"2407.00203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T19:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"2ea50ee16b93989d554d076233edfad6487e84242fe32009a5404c15f5bff3d5","abstract_canon_sha256":"4d1cfa58863f34fd2f517f9a0d90504d1f79b79255935f3365fd93bf713068ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:15.709953Z","signature_b64":"l/atXb2dDQdnz5euR46KM0U3yV9ZXukEIOXbc3JR9UnN+Tanx5OB/PmV/9c4KzwLDet4Uoh1Ab8skrSSM4GOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b751a94b1ff50a5f65c849bb5c280798c678b06ec2916848ed1a7d05a0ad54ef","last_reissued_at":"2026-07-05T08:38:15.709459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:15.709459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglu Zhu, Jingxiong Li, Kai Zhang, Lin Yang, Tao Lin, Xingheng Lyu, Yixuan Si, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui","submitted_at":"2024-06-28T19:18:09Z","abstract_excerpt":"Vision Language Models (VLMs) like CLIP have attracted substantial attention in pathology, serving as backbones for applications such as zero-shot image classification and Whole Slide Image (WSI) analysis. Additionally, they can function as vision encoders when combined with large language models (LLMs) to support broader capabilities. Current efforts to train pathology VLMs rely on pathology image-text pairs from platforms like PubMed, YouTube, and Twitter, which provide limited, unscalable data with generally suboptimal image quality. In this work, we leverage large-scale WSI datasets like T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00203","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/2407.00203/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":"2407.00203","created_at":"2026-07-05T08:38:15.709529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00203v1","created_at":"2026-07-05T08:38:15.709529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00203","created_at":"2026-07-05T08:38:15.709529+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5I2SSY76UFF","created_at":"2026-07-05T08:38:15.709529+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5I2SSY76UFF6ZOI","created_at":"2026-07-05T08:38:15.709529+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5I2SSY7","created_at":"2026-07-05T08:38:15.709529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":277,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03635","citing_title":"A Generative Foundation Model for Multimodal Histopathology","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13564","citing_title":"Memory in the Age of AI Agents","ref_index":210,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD","json":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD.json","graph_json":"https://pith.science/api/pith-number/W5I2SSY76UFF6ZOIJG5VYKAHTD/graph.json","events_json":"https://pith.science/api/pith-number/W5I2SSY76UFF6ZOIJG5VYKAHTD/events.json","paper":"https://pith.science/paper/W5I2SSY7"},"agent_actions":{"view_html":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD","download_json":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD.json","view_paper":"https://pith.science/paper/W5I2SSY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00203&json=true","fetch_graph":"https://pith.science/api/pith-number/W5I2SSY76UFF6ZOIJG5VYKAHTD/graph.json","fetch_events":"https://pith.science/api/pith-number/W5I2SSY76UFF6ZOIJG5VYKAHTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD/action/storage_attestation","attest_author":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD/action/author_attestation","sign_citation":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD/action/citation_signature","submit_replication":"https://pith.science/pith/W5I2SSY76UFF6ZOIJG5VYKAHTD/action/replication_record"}},"created_at":"2026-07-05T08:38:15.709529+00:00","updated_at":"2026-07-05T08:38:15.709529+00:00"}