{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NDIP27JOQ2GI5TEW5OSJGK6HCP","short_pith_number":"pith:NDIP27JO","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"},"canonical_sha256":"68d0fd7d2e868c8ecc96eba4932bc713fa6fcd7c8a770e0219c54df830b848ba","source":{"kind":"arxiv","id":"2003.10286","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10286","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10286v1","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10286","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"NDIP27JOQ2GI","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"NDIP27JOQ2GI5TEW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"NDIP27JO","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NDIP27JOQ2GI5TEW5OSJGK6HCP","target":"record","payload":{"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"},"canonical_sha256":"68d0fd7d2e868c8ecc96eba4932bc713fa6fcd7c8a770e0219c54df830b848ba","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"},"source_kind":"arxiv","source_id":"2003.10286","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdhflDs8soKcYBwrbI6fpCXw9EjmUD0kTgnJmIPSYqAzPyCZ1gFmvNiGQebNHpTs/q0JLX87eVCzyBDTBz0WAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:17:47.554504Z"},"content_sha256":"4706419a3bbb310751080fc8b0d38f225cb3c0de9a0c42db605db1fc06c38bcf","schema_version":"1.0","event_id":"sha256:4706419a3bbb310751080fc8b0d38f225cb3c0de9a0c42db605db1fc06c38bcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NDIP27JOQ2GI5TEW5OSJGK6HCP","target":"graph","payload":{"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"},"verdict_id":"234bda4a-a97e-42bc-87f9-c037f6bc8997"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C+h0OGNcPtbuHLqC8OdKkxLbqhE4+lzHp72z9Z2FcT0Bt2KBN+mmZtTSG7poYli0R++1cUqyeRUAWTlv7bWDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:17:47.555534Z"},"content_sha256":"be0dcfbfd9724d07780654d71fb13ffeee67915d262b92e0136dc44a06677326","schema_version":"1.0","event_id":"sha256:be0dcfbfd9724d07780654d71fb13ffeee67915d262b92e0136dc44a06677326"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/bundle.json","state_url":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T10:17:47Z","links":{"resolver":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP","bundle":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/bundle.json","state":"https://pith.science/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDIP27JOQ2GI5TEW5OSJGK6HCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NDIP27JOQ2GI5TEW5OSJGK6HCP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7d90650c41118c44b4714d4f5e346c41bc98b2570e8867fb21fd37f16b77d852","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-07T17:55:41Z","title_canon_sha256":"81632873afec56f9215e42e974206a080dc643bae35d6ca32526915cfdae1b6e"},"schema_version":"1.0","source":{"id":"2003.10286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10286","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10286v1","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10286","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"NDIP27JOQ2GI","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"NDIP27JOQ2GI5TEW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"NDIP27JO","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:be0dcfbfd9724d07780654d71fb13ffeee67915d262b92e0136dc44a06677326","target":"graph","created_at":"2026-05-17T23:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"To our best knowledge, this is the first dataset for pathology VQA."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PathVQA is the first public dataset of over 32,000 questions on nearly 5,000 pathology images for medical visual question answering."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images."}],"snapshot_sha256":"59db6ca86cbe0010dcd23bcee75e82b70e654adc32378bbc00f0c8a950518060"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"11f563d420e848fc12ed11ce6c9c7194fc951ac294c4303b8d3a2c266f10f412"},"paper":{"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","authors_text":"Eric Xing, Luntian Mou, Pengtao Xie, Xuehai He, Yichen Zhang","cross_cats":["cs.AI"],"headline":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-07T17:55:41Z","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering"},"references":{"count":34,"internal_anchors":4,"resolved_work":34,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Vqa: Visual question answering","work_id":"b5a5494b-c898-4d81-8c7a-27fa15869e0f","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A multi-world approach to question answering about real-world scenes based on uncertain input","work_id":"bad71b41-4475-4537-8fbf-9c90209ec63a","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Image question answering: A visual semantic embedding model and a new dataset","work_id":"93fdc4ae-0cf3-4648-a98d-6ec3c285f604","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Clevr: A diagnostic dataset for compositional language and elementary visual reasoning","work_id":"75988bdb-b9c2-48eb-93e8-e7617400c787","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Making the v in vqa matter: Elevating the role of image understanding in visual question answering","work_id":"429fd41f-767c-49e9-bdb0-3b99e1135349","year":2017}],"snapshot_sha256":"1536d37929198a432a2fd04ab19840d0a28cb90c24b55b554728167450b3137b"},"source":{"id":"2003.10286","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:09:48.556384Z","id":"234bda4a-a97e-42bc-87f9-c037f6bc8997","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"The first pathology visual question answering dataset is created with 32,799 manually verified questions from 4,998 images.","strongest_claim":"To our best knowledge, this is the first dataset for pathology VQA.","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."}},"verdict_id":"234bda4a-a97e-42bc-87f9-c037f6bc8997"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4706419a3bbb310751080fc8b0d38f225cb3c0de9a0c42db605db1fc06c38bcf","target":"record","created_at":"2026-05-17T23:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7d90650c41118c44b4714d4f5e346c41bc98b2570e8867fb21fd37f16b77d852","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-07T17:55:41Z","title_canon_sha256":"81632873afec56f9215e42e974206a080dc643bae35d6ca32526915cfdae1b6e"},"schema_version":"1.0","source":{"id":"2003.10286","kind":"arxiv","version":1}},"canonical_sha256":"68d0fd7d2e868c8ecc96eba4932bc713fa6fcd7c8a770e0219c54df830b848ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68d0fd7d2e868c8ecc96eba4932bc713fa6fcd7c8a770e0219c54df830b848ba","first_computed_at":"2026-05-17T23:38:53.418891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.418891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qeO25GViv3dxDzIQBUmN/hgkmqlGFD67wpI+dVbnDRrjsZwdPmAzD2Cm5wL08xzpnprc5yAg/P6DptGQP824DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.419539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.10286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4706419a3bbb310751080fc8b0d38f225cb3c0de9a0c42db605db1fc06c38bcf","sha256:be0dcfbfd9724d07780654d71fb13ffeee67915d262b92e0136dc44a06677326"],"state_sha256":"bf3fa6a7f086515aa0eb35c13642a1a3a9bdc6b1a53e06f96230b60334930b74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f0hDOtgYwD2GWLPHAVnOmZu1j9GEe4kL9ZjwESdXT0L9aPU0VHMXO3HZM4qw3ZvsAycWkutToCDEHCftoUncCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T10:17:47.559831Z","bundle_sha256":"3a08c659049cc709bc6e47ed8931d75ccbc9f9112fd76ae18162d57f421419bc"}}