{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NDIP27JOQ2GI5TEW5OSJGK6HCP","short_pith_number":"pith:NDIP27JO","schema_version":"1.0","canonical_sha256":"68d0fd7d2e868c8ecc96eba4932bc713fa6fcd7c8a770e0219c54df830b848ba","source":{"kind":"arxiv","id":"2003.10286","version":1},"attestation_state":"computed","paper":{"title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Xing, Luntian Mou, Pengtao Xie, Xuehai He, Yichen Zhang","submitted_at":"2020-03-07T17:55:41Z","abstract_excerpt":"Is it possible to develop an \"AI Pathologist\" to pass the board-certified examination of the American Board of Pathology? To achieve this goal, the first step is to create a visual question answering (VQA) dataset where the AI agent is presented with a pathology image together with a question and is asked to give the correct answer. Our work makes the first attempt to build such a dataset. Different from creating general-domain VQA datasets where the images are widely accessible and there are many crowdsourcing workers available and capable of generating question-answer pairs, developing a med"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2003.10286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-07T17:55:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"81632873afec56f9215e42e974206a080dc643bae35d6ca32526915cfdae1b6e","abstract_canon_sha256":"7d90650c41118c44b4714d4f5e346c41bc98b2570e8867fb21fd37f16b77d852"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.419539Z","signature_b64":"qeO25GViv3dxDzIQBUmN/hgkmqlGFD67wpI+dVbnDRrjsZwdPmAzD2Cm5wL08xzpnprc5yAg/P6DptGQP824DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68d0fd7d2e868c8ecc96eba4932bc713fa6fcd7c8a770e0219c54df830b848ba","last_reissued_at":"2026-05-17T23:38:53.418891Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.418891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Xing, Luntian Mou, Pengtao Xie, Xuehai He, Yichen Zhang","submitted_at":"2020-03-07T17:55:41Z","abstract_excerpt":"Is it possible to develop an \"AI Pathologist\" to pass the board-certified examination of the American Board of Pathology? To achieve this goal, the first step is to create a visual question answering (VQA) dataset where the AI agent is presented with a pathology image together with a question and is asked to give the correct answer. Our work makes the first attempt to build such a dataset. Different from creating general-domain VQA datasets where the images are widely accessible and there are many crowdsourcing workers available and capable of generating question-answer pairs, developing a med"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"To our best knowledge, this is the first dataset for pathology VQA.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That questions automatically generated from image captions using NLP, followed by manual checks, produce medically accurate and representative questions that pathologists would actually ask when viewing the images.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PathVQA is the first public dataset of over 32,000 questions on nearly 5,000 pathology images for medical visual question answering.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"59db6ca86cbe0010dcd23bcee75e82b70e654adc32378bbc00f0c8a950518060"},"source":{"id":"2003.10286","kind":"arxiv","version":1},"verdict":{"id":"234bda4a-a97e-42bc-87f9-c037f6bc8997","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:09:48.556384Z","strongest_claim":"To our best knowledge, this is the first dataset for pathology VQA.","one_line_summary":"PathVQA is the first public dataset of over 32,000 questions on nearly 5,000 pathology images for medical visual question answering.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That questions automatically generated from image captions using NLP, followed by manual checks, produce medically accurate and representative questions that pathologists would actually ask when viewing the images.","pith_extraction_headline":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images."},"references":{"count":34,"sample":[{"doi":"","year":2015,"title":"Vqa: Visual question answering","work_id":"b5a5494b-c898-4d81-8c7a-27fa15869e0f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"A multi-world approach to question answering about real-world scenes based on uncertain input","work_id":"bad71b41-4475-4537-8fbf-9c90209ec63a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Image question answering: A visual semantic embedding model and a new dataset","work_id":"93fdc4ae-0cf3-4648-a98d-6ec3c285f604","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Clevr: A diagnostic dataset for compositional language and elementary visual reasoning","work_id":"75988bdb-b9c2-48eb-93e8-e7617400c787","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Making the v in vqa matter: Elevating the role of image understanding in visual question answering","work_id":"429fd41f-767c-49e9-bdb0-3b99e1135349","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":34,"snapshot_sha256":"1536d37929198a432a2fd04ab19840d0a28cb90c24b55b554728167450b3137b","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"11f563d420e848fc12ed11ce6c9c7194fc951ac294c4303b8d3a2c266f10f412"},"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":"2003.10286","created_at":"2026-05-17T23:38:53.418982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.10286v1","created_at":"2026-05-17T23:38:53.418982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10286","created_at":"2026-05-17T23:38:53.418982+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDIP27JOQ2GI","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDIP27JOQ2GI5TEW","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDIP27JO","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":44,"internal_anchor_count":44,"sample":[{"citing_arxiv_id":"2605.23559","citing_title":"PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23629","citing_title":"DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2306.00890","citing_title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2412.04468","citing_title":"NVILA: Efficient Frontier Visual Language Models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22080","citing_title":"JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21979","citing_title":"Benchmarking and Mitigating Sycophancy in Medical Vision Language Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20525","citing_title":"NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15574","citing_title":"MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18313","citing_title":"Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18111","citing_title":"How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20158","citing_title":"Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15766","citing_title":"BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21979","citing_title":"Benchmarking and Mitigating Sycophancy in Medical Vision Language Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22258","citing_title":"Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17652","citing_title":"TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2512.22278","citing_title":"FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03054","citing_title":"IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":122,"is_internal_anchor":true},{"citing_arxiv_id":"2602.12705","citing_title":"MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2602.21950","citing_title":"MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2603.06665","citing_title":"Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.24649","citing_title":"MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP","json":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP.json","graph_json":"https://pith.science/api/pith-number/NDIP27JOQ2GI5TEW5OSJGK6HCP/graph.json","events_json":"https://pith.science/api/pith-number/NDIP27JOQ2GI5TEW5OSJGK6HCP/events.json","paper":"https://pith.science/paper/NDIP27JO"},"agent_actions":{"view_html":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP","download_json":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP.json","view_paper":"https://pith.science/paper/NDIP27JO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.10286&json=true","fetch_graph":"https://pith.science/api/pith-number/NDIP27JOQ2GI5TEW5OSJGK6HCP/graph.json","fetch_events":"https://pith.science/api/pith-number/NDIP27JOQ2GI5TEW5OSJGK6HCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/action/storage_attestation","attest_author":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/action/author_attestation","sign_citation":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/action/citation_signature","submit_replication":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/action/replication_record"}},"created_at":"2026-05-17T23:38:53.418982+00:00","updated_at":"2026-05-17T23:38:53.418982+00:00"}