{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LHK23AIPKILSQ3WUXCRNT2FQQR","short_pith_number":"pith:LHK23AIP","schema_version":"1.0","canonical_sha256":"59d5ad810f5217286ed4b8a2d9e8b08469c651a876081018764f4f90b84ae9a4","source":{"kind":"arxiv","id":"1802.08218","version":4},"attestation_state":"computed","paper":{"title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Abigale J. Stangl, Anhong Guo, Chi Lin, Danna Gurari, Jeffrey P. Bigham, Jiebo Luo, Kristen Grauman, Qing Li","submitted_at":"2018-02-22T18:16:53Z","abstract_excerpt":"The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising from a natural VQA setting. VizWiz consists of over 31,000 visual questions originating from blind people who each took a picture using a mobile phone and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. VizWiz differs from the many existing VQA datasets because (1) images are captured by blind photographers and so a"},"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":"1802.08218","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-22T18:16:53Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"7eed89a0b1f5823cf0cefdb824ca21b11073184605d8962673a5a49053f21cf9","abstract_canon_sha256":"5d7e01e1742c304cbff1b1d26ce5791bcfe2aa5dc545e13d5ea11846a5dace4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:28.049459Z","signature_b64":"cHWWkokctiVfmyWSKCxlX7x07kSFKyUZcKr89CqjqMgXK3RNz69vfipr6wuuGjPCsXrJD8C5TSouPEcOxMEJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d5ad810f5217286ed4b8a2d9e8b08469c651a876081018764f4f90b84ae9a4","last_reissued_at":"2026-05-18T00:15:28.048754Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:28.048754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Abigale J. Stangl, Anhong Guo, Chi Lin, Danna Gurari, Jeffrey P. Bigham, Jiebo Luo, Kristen Grauman, Qing Li","submitted_at":"2018-02-22T18:16:53Z","abstract_excerpt":"The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising from a natural VQA setting. VizWiz consists of over 31,000 visual questions originating from blind people who each took a picture using a mobile phone and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. VizWiz differs from the many existing VQA datasets because (1) images are captured by blind photographers and so a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08218","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.08218","created_at":"2026-05-18T00:15:28.048851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08218v4","created_at":"2026-05-18T00:15:28.048851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08218","created_at":"2026-05-18T00:15:28.048851+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHK23AIPKILS","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHK23AIPKILSQ3WU","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHK23AIP","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2406.11354","citing_title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","ref_index":17,"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":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18903","citing_title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21420","citing_title":"ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16930","citing_title":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17488","citing_title":"AutoVQA-G: Self-Improving Agentic Framework for Automated Visual Question Answering and Grounding Annotation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR","json":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR.json","graph_json":"https://pith.science/api/pith-number/LHK23AIPKILSQ3WUXCRNT2FQQR/graph.json","events_json":"https://pith.science/api/pith-number/LHK23AIPKILSQ3WUXCRNT2FQQR/events.json","paper":"https://pith.science/paper/LHK23AIP"},"agent_actions":{"view_html":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR","download_json":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR.json","view_paper":"https://pith.science/paper/LHK23AIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08218&json=true","fetch_graph":"https://pith.science/api/pith-number/LHK23AIPKILSQ3WUXCRNT2FQQR/graph.json","fetch_events":"https://pith.science/api/pith-number/LHK23AIPKILSQ3WUXCRNT2FQQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR/action/storage_attestation","attest_author":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR/action/author_attestation","sign_citation":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR/action/citation_signature","submit_replication":"https://pith.science/pith/LHK23AIPKILSQ3WUXCRNT2FQQR/action/replication_record"}},"created_at":"2026-05-18T00:15:28.048851+00:00","updated_at":"2026-05-18T00:15:28.048851+00:00"}