{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M7VCQ5V3ZG5XDHR4S6QH3LPUCR","short_pith_number":"pith:M7VCQ5V3","schema_version":"1.0","canonical_sha256":"67ea2876bbc9bb719e3c97a07dadf414522b19723a67a59af927a00e23becf72","source":{"kind":"arxiv","id":"2501.03225","version":2},"attestation_state":"computed","paper":{"title":"Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alejandro Lozano, Anjiang Wei, Chenyu Wang, Elaine Sui, James Burgess, Josiah Aklilu, Ludwig Schmidt, Serena Yeung-Levy, Xiaohan Wang, Yiming Liu, Yuchang Su, Yuhui Zhang","submitted_at":"2025-01-06T18:57:31Z","abstract_excerpt":"The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural language responses. To address this, we introduce AutoConverter, an agentic framework that automatically converts these open-ended questions into multiple-choice format, enabling objective evaluation while reducing the costly multiple-choice question creation process. Our experiments demonstrate that AutoConverter can generate corre"},"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":"2501.03225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T18:57:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"title_canon_sha256":"43199180fbd6ee32aa4c4172baf2314b3ef4a2b97ef8899762f51fd4d1445115","abstract_canon_sha256":"3946cbfc0d72fad881d68d572a6f3888fd9b271117f5ce67b1a145036d128b80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:40.433366Z","signature_b64":"JljpVVSFjm+Uak6fH8WvvNerKeXcuVUN2viNQcmU9FUhdFUOyW6RywhLr8v5oyG7pDOMC5KRuMk6BHbEArd7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ea2876bbc9bb719e3c97a07dadf414522b19723a67a59af927a00e23becf72","last_reissued_at":"2026-07-05T10:46:40.432852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:40.432852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alejandro Lozano, Anjiang Wei, Chenyu Wang, Elaine Sui, James Burgess, Josiah Aklilu, Ludwig Schmidt, Serena Yeung-Levy, Xiaohan Wang, Yiming Liu, Yuchang Su, Yuhui Zhang","submitted_at":"2025-01-06T18:57:31Z","abstract_excerpt":"The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural language responses. To address this, we introduce AutoConverter, an agentic framework that automatically converts these open-ended questions into multiple-choice format, enabling objective evaluation while reducing the costly multiple-choice question creation process. Our experiments demonstrate that AutoConverter can generate corre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03225","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.03225/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":"2501.03225","created_at":"2026-07-05T10:46:40.432915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03225v2","created_at":"2026-07-05T10:46:40.432915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03225","created_at":"2026-07-05T10:46:40.432915+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7VCQ5V3ZG5X","created_at":"2026-07-05T10:46:40.432915+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7VCQ5V3ZG5XDHR4","created_at":"2026-07-05T10:46:40.432915+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7VCQ5V3","created_at":"2026-07-05T10:46:40.432915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10219","citing_title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR","json":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR.json","graph_json":"https://pith.science/api/pith-number/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/graph.json","events_json":"https://pith.science/api/pith-number/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/events.json","paper":"https://pith.science/paper/M7VCQ5V3"},"agent_actions":{"view_html":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR","download_json":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR.json","view_paper":"https://pith.science/paper/M7VCQ5V3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03225&json=true","fetch_graph":"https://pith.science/api/pith-number/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/graph.json","fetch_events":"https://pith.science/api/pith-number/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/action/storage_attestation","attest_author":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/action/author_attestation","sign_citation":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/action/citation_signature","submit_replication":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/action/replication_record"}},"created_at":"2026-07-05T10:46:40.432915+00:00","updated_at":"2026-07-05T10:46:40.432915+00:00"}