{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VN6UJU6TNW3KHGSTXXPZRFFDYM","short_pith_number":"pith:VN6UJU6T","schema_version":"1.0","canonical_sha256":"ab7d44d3d36db6a39a53bddf9894a3c32df281399ee172736761f8e288b9a95b","source":{"kind":"arxiv","id":"2607.19261","version":1},"attestation_state":"computed","paper":{"title":"PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dachun Zhao, Dankai Liao, Linghan Cai, Qiaochu Xue, Tianyi Zhang, Xinyue Zhang, Yueming Jin, Yufeng Wu, Zeyu Liu","submitted_at":"2026-07-21T16:33:44Z","abstract_excerpt":"Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scale evidence. However, most existing pathology benchmarks evaluate models on pre-cropped patches or pre-extracted slide features, leaving their ability to acquire evidence directly from gigapixel WSIs largely untested. We introduce PathAgentBench, a benchmark for evaluating evidence-seeking vision-language models (VLMs) across four complementary capabilities: image-to-text matching for evidence interpretation, text-to-image retrieval for evidence"},"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":"2607.19261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T16:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0c0ea7826ea8e3c3f0ea81f69fa1163e5815a704a4d83107e71265a2a9bab61","abstract_canon_sha256":"84834f2cd6a0ff5eb9e9d5a1f0ab33feec6513629271ccba773e1ade0bc74501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:16.995377Z","signature_b64":"bV8s5qzT46gVj83kB9b7Mp03LEcEFdLsZmqtnwEwsVrACxY02wYX6xxCDYFpYQzIrelqXz2+gGVoHD95KsoXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7d44d3d36db6a39a53bddf9894a3c32df281399ee172736761f8e288b9a95b","last_reissued_at":"2026-07-22T01:24:16.994534Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:16.994534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dachun Zhao, Dankai Liao, Linghan Cai, Qiaochu Xue, Tianyi Zhang, Xinyue Zhang, Yueming Jin, Yufeng Wu, Zeyu Liu","submitted_at":"2026-07-21T16:33:44Z","abstract_excerpt":"Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scale evidence. However, most existing pathology benchmarks evaluate models on pre-cropped patches or pre-extracted slide features, leaving their ability to acquire evidence directly from gigapixel WSIs largely untested. We introduce PathAgentBench, a benchmark for evaluating evidence-seeking vision-language models (VLMs) across four complementary capabilities: image-to-text matching for evidence interpretation, text-to-image retrieval for evidence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19261","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/2607.19261/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":"2607.19261","created_at":"2026-07-22T01:24:16.994968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19261v1","created_at":"2026-07-22T01:24:16.994968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19261","created_at":"2026-07-22T01:24:16.994968+00:00"},{"alias_kind":"pith_short_12","alias_value":"VN6UJU6TNW3K","created_at":"2026-07-22T01:24:16.994968+00:00"},{"alias_kind":"pith_short_16","alias_value":"VN6UJU6TNW3KHGST","created_at":"2026-07-22T01:24:16.994968+00:00"},{"alias_kind":"pith_short_8","alias_value":"VN6UJU6T","created_at":"2026-07-22T01:24:16.994968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08648","citing_title":"Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM","json":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM.json","graph_json":"https://pith.science/api/pith-number/VN6UJU6TNW3KHGSTXXPZRFFDYM/graph.json","events_json":"https://pith.science/api/pith-number/VN6UJU6TNW3KHGSTXXPZRFFDYM/events.json","paper":"https://pith.science/paper/VN6UJU6T"},"agent_actions":{"view_html":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM","download_json":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM.json","view_paper":"https://pith.science/paper/VN6UJU6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19261&json=true","fetch_graph":"https://pith.science/api/pith-number/VN6UJU6TNW3KHGSTXXPZRFFDYM/graph.json","fetch_events":"https://pith.science/api/pith-number/VN6UJU6TNW3KHGSTXXPZRFFDYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM/action/storage_attestation","attest_author":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM/action/author_attestation","sign_citation":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM/action/citation_signature","submit_replication":"https://pith.science/pith/VN6UJU6TNW3KHGSTXXPZRFFDYM/action/replication_record"}},"created_at":"2026-07-22T01:24:16.994968+00:00","updated_at":"2026-07-22T01:24:16.994968+00:00"}