{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XBWSRWONCD3PTPGATFGD7O3FFR","short_pith_number":"pith:XBWSRWON","schema_version":"1.0","canonical_sha256":"b86d28d9cd10f6f9bcc0994c3fbb652c65f45bf83f90c3ace57c6826d4baca5a","source":{"kind":"arxiv","id":"1612.06530","version":2},"attestation_state":"computed","paper":{"title":"Automatic Generation of Grounded Visual Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiawan Zhang, Lizhen Qu, Shaodi You, Shijie Zhang, Zhenglu Yang","submitted_at":"2016-12-20T07:20:16Z","abstract_excerpt":"In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image. Visual question generation is an emerging topic which aims to ask questions in natural language based on visual input. To the best of our knowledge, it lacks automatic methods to generate meaningful questions with various types for the same visual input. To circumvent the problem, we propose a model that automatically generates visually grounded questions with varying types. Our model takes as input both images and the captions generated by a dense caption model, "},"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":"1612.06530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-20T07:20:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2e3a442ba8a9adc5cdce090e31b3f4974eb9d9d73688a7b24d7325336dd06712","abstract_canon_sha256":"292d15fc7e3b3c5f3f8702be6489a95cf4b457fcaa0029ba68dec9e3cd2204ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:35.411071Z","signature_b64":"eJ7t1+fa3gEqGlSHgD+mryWs+lR0TU/9lGlJcJ5qVbUNpW90Q9UKRW2cGAnMsiflJPY9CJ1HgGmor+6EggRfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86d28d9cd10f6f9bcc0994c3fbb652c65f45bf83f90c3ace57c6826d4baca5a","last_reissued_at":"2026-05-18T00:43:35.410692Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:35.410692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Generation of Grounded Visual Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiawan Zhang, Lizhen Qu, Shaodi You, Shijie Zhang, Zhenglu Yang","submitted_at":"2016-12-20T07:20:16Z","abstract_excerpt":"In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image. Visual question generation is an emerging topic which aims to ask questions in natural language based on visual input. To the best of our knowledge, it lacks automatic methods to generate meaningful questions with various types for the same visual input. To circumvent the problem, we propose a model that automatically generates visually grounded questions with varying types. Our model takes as input both images and the captions generated by a dense caption model, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06530","kind":"arxiv","version":2},"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":"1612.06530","created_at":"2026-05-18T00:43:35.410752+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.06530v2","created_at":"2026-05-18T00:43:35.410752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06530","created_at":"2026-05-18T00:43:35.410752+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBWSRWONCD3P","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBWSRWONCD3PTPGA","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBWSRWON","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR","json":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR.json","graph_json":"https://pith.science/api/pith-number/XBWSRWONCD3PTPGATFGD7O3FFR/graph.json","events_json":"https://pith.science/api/pith-number/XBWSRWONCD3PTPGATFGD7O3FFR/events.json","paper":"https://pith.science/paper/XBWSRWON"},"agent_actions":{"view_html":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR","download_json":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR.json","view_paper":"https://pith.science/paper/XBWSRWON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.06530&json=true","fetch_graph":"https://pith.science/api/pith-number/XBWSRWONCD3PTPGATFGD7O3FFR/graph.json","fetch_events":"https://pith.science/api/pith-number/XBWSRWONCD3PTPGATFGD7O3FFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR/action/storage_attestation","attest_author":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR/action/author_attestation","sign_citation":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR/action/citation_signature","submit_replication":"https://pith.science/pith/XBWSRWONCD3PTPGATFGD7O3FFR/action/replication_record"}},"created_at":"2026-05-18T00:43:35.410752+00:00","updated_at":"2026-05-18T00:43:35.410752+00:00"}