{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6RCM7YHO3JRC7JLTQ2SU7WMJ3A","short_pith_number":"pith:6RCM7YHO","schema_version":"1.0","canonical_sha256":"f444cfe0eeda622fa57386a54fd989d8093fd931cac3fec83275cf5e77db5c99","source":{"kind":"arxiv","id":"2208.01813","version":3},"attestation_state":"computed","paper":{"title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chetan Ramaiah, Joseph F. JaJa, Jun Wang, Larry S. Davis, Mingfei Gao, Ramprasaath R. Selvaraju, Ran Xu, Yuqian Hu","submitted_at":"2022-08-03T02:18:09Z","abstract_excerpt":"Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs. However, we observe that, in general, the scene text is not fully exploited in the existing datasets -- only a small portion of the text in each image participates in the annotated QA activities. This results in a huge waste of useful information. To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly uti"},"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":"2208.01813","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-03T02:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"82b6021323e3827693cbd533eb5c6e24307c62b2a33c9e5c74c247bb74c65105","abstract_canon_sha256":"d621e53483098dc9c9dae7c69834ffe408f34d8562a86efebf26f6ef3abc82dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:30.590764Z","signature_b64":"IVfnW+G38O0c5pRyZPIa/QoT/6FoMe9aLE6f6I0L9cEGO1rEfDmGb6i1yOrjNJlTamxJKeI/5VOQ4uH9CAQrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f444cfe0eeda622fa57386a54fd989d8093fd931cac3fec83275cf5e77db5c99","last_reissued_at":"2026-07-05T05:04:30.590338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:30.590338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chetan Ramaiah, Joseph F. JaJa, Jun Wang, Larry S. Davis, Mingfei Gao, Ramprasaath R. Selvaraju, Ran Xu, Yuqian Hu","submitted_at":"2022-08-03T02:18:09Z","abstract_excerpt":"Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs. However, we observe that, in general, the scene text is not fully exploited in the existing datasets -- only a small portion of the text in each image participates in the annotated QA activities. This results in a huge waste of useful information. To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly uti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01813","kind":"arxiv","version":3},"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/2208.01813/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":"2208.01813","created_at":"2026-07-05T05:04:30.590395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01813v3","created_at":"2026-07-05T05:04:30.590395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01813","created_at":"2026-07-05T05:04:30.590395+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RCM7YHO3JRC","created_at":"2026-07-05T05:04:30.590395+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RCM7YHO3JRC7JLT","created_at":"2026-07-05T05:04:30.590395+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RCM7YHO","created_at":"2026-07-05T05:04:30.590395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.03939","citing_title":"Visual question answering: from early developments to recent advances -- a survey","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A","json":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A.json","graph_json":"https://pith.science/api/pith-number/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/graph.json","events_json":"https://pith.science/api/pith-number/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/events.json","paper":"https://pith.science/paper/6RCM7YHO"},"agent_actions":{"view_html":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A","download_json":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A.json","view_paper":"https://pith.science/paper/6RCM7YHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01813&json=true","fetch_graph":"https://pith.science/api/pith-number/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/graph.json","fetch_events":"https://pith.science/api/pith-number/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/action/storage_attestation","attest_author":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/action/author_attestation","sign_citation":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/action/citation_signature","submit_replication":"https://pith.science/pith/6RCM7YHO3JRC7JLTQ2SU7WMJ3A/action/replication_record"}},"created_at":"2026-07-05T05:04:30.590395+00:00","updated_at":"2026-07-05T05:04:30.590395+00:00"}