{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EXXRNEXUQ2KJTUVFJH33FFQELU","short_pith_number":"pith:EXXRNEXU","schema_version":"1.0","canonical_sha256":"25ef1692f4869499d2a549f7b296045d0547ae0f1ea911dd61a90d92da48e661","source":{"kind":"arxiv","id":"2307.04643","version":1},"attestation_state":"computed","paper":{"title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Richard Baraniuk, Zichao Wang","submitted_at":"2023-07-07T08:14:15Z","abstract_excerpt":"We study the new problem of automatic question generation (QG) from multi-modal sources containing images and texts, significantly expanding the scope of most of the existing work that focuses exclusively on QG from only textual sources. We propose a simple solution for our new problem, called MultiQG-TI, which enables a text-only question generator to process visual input in addition to textual input. Specifically, we leverage an image-to-text model and an optical character recognition model to obtain the textual description of the image and extract any texts in the image, respectively, and t"},"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":"2307.04643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-07T08:14:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b218b3a1080123bb078eb849bbef4800b0d202e470498242f92eca892e3f0d5","abstract_canon_sha256":"c7b696156723b51b9eb7761e6f7f8446699f55fd86f3cf97d3a1e718cbeb1d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:15.809422Z","signature_b64":"GN1hUc2A/U3up8wtRbEe7TLeFVZC6iVSo0SYLVsHOiKyVjM8LmELO+Px04Py7IENYsklj38SwIezvId/kHTEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ef1692f4869499d2a549f7b296045d0547ae0f1ea911dd61a90d92da48e661","last_reissued_at":"2026-07-05T06:29:15.808989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:15.808989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Richard Baraniuk, Zichao Wang","submitted_at":"2023-07-07T08:14:15Z","abstract_excerpt":"We study the new problem of automatic question generation (QG) from multi-modal sources containing images and texts, significantly expanding the scope of most of the existing work that focuses exclusively on QG from only textual sources. We propose a simple solution for our new problem, called MultiQG-TI, which enables a text-only question generator to process visual input in addition to textual input. Specifically, we leverage an image-to-text model and an optical character recognition model to obtain the textual description of the image and extract any texts in the image, respectively, and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04643","kind":"arxiv","version":1},"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/2307.04643/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":"2307.04643","created_at":"2026-07-05T06:29:15.809044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04643v1","created_at":"2026-07-05T06:29:15.809044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04643","created_at":"2026-07-05T06:29:15.809044+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXXRNEXUQ2KJ","created_at":"2026-07-05T06:29:15.809044+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXXRNEXUQ2KJTUVF","created_at":"2026-07-05T06:29:15.809044+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXXRNEXU","created_at":"2026-07-05T06:29:15.809044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18772","citing_title":"Beyond the Textual: Generating Coherent Visual Options for MCQs","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU","json":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU.json","graph_json":"https://pith.science/api/pith-number/EXXRNEXUQ2KJTUVFJH33FFQELU/graph.json","events_json":"https://pith.science/api/pith-number/EXXRNEXUQ2KJTUVFJH33FFQELU/events.json","paper":"https://pith.science/paper/EXXRNEXU"},"agent_actions":{"view_html":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU","download_json":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU.json","view_paper":"https://pith.science/paper/EXXRNEXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04643&json=true","fetch_graph":"https://pith.science/api/pith-number/EXXRNEXUQ2KJTUVFJH33FFQELU/graph.json","fetch_events":"https://pith.science/api/pith-number/EXXRNEXUQ2KJTUVFJH33FFQELU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU/action/storage_attestation","attest_author":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU/action/author_attestation","sign_citation":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU/action/citation_signature","submit_replication":"https://pith.science/pith/EXXRNEXUQ2KJTUVFJH33FFQELU/action/replication_record"}},"created_at":"2026-07-05T06:29:15.809044+00:00","updated_at":"2026-07-05T06:29:15.809044+00:00"}