{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M7VCQ5V3ZG5XDHR4S6QH3LPUCR","short_pith_number":"pith:M7VCQ5V3","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"},"canonical_sha256":"67ea2876bbc9bb719e3c97a07dadf414522b19723a67a59af927a00e23becf72","source":{"kind":"arxiv","id":"2501.03225","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03225","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03225v2","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03225","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"M7VCQ5V3ZG5X","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"M7VCQ5V3ZG5XDHR4","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"M7VCQ5V3","created_at":"2026-07-05T10:46:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M7VCQ5V3ZG5XDHR4S6QH3LPUCR","target":"record","payload":{"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"},"canonical_sha256":"67ea2876bbc9bb719e3c97a07dadf414522b19723a67a59af927a00e23becf72","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"},"source_kind":"arxiv","source_id":"2501.03225","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N89OtxYJTcxmP+tw0KnX1RsU+b1wdrnmL5/obURumr3Pp/G6a8MxSTnE9wTNk829gPufGlBPeYGelagU0HLfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:39:05.422892Z"},"content_sha256":"b1e91c06c897c224da394f19be57055af18ccbeb3c211c6c321fb63b6cf011a7","schema_version":"1.0","event_id":"sha256:b1e91c06c897c224da394f19be57055af18ccbeb3c211c6c321fb63b6cf011a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M7VCQ5V3ZG5XDHR4S6QH3LPUCR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYRL6HKRNpHN0nGDFQpd77LWdJudQBhwihsjmBcmIG7Xf+T8Zs2kP+vEoNvuvH9xkg9OsCD6RVNjSIKpRB/ICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:39:05.423831Z"},"content_sha256":"cb1272f9d696361cdc084fc61b5e5424221ad9a5679ac2c024c68df64e86bb77","schema_version":"1.0","event_id":"sha256:cb1272f9d696361cdc084fc61b5e5424221ad9a5679ac2c024c68df64e86bb77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/bundle.json","state_url":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T07:39:05Z","links":{"resolver":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR","bundle":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/bundle.json","state":"https://pith.science/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7VCQ5V3ZG5XDHR4S6QH3LPUCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M7VCQ5V3ZG5XDHR4S6QH3LPUCR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3946cbfc0d72fad881d68d572a6f3888fd9b271117f5ce67b1a145036d128b80","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T18:57:31Z","title_canon_sha256":"43199180fbd6ee32aa4c4172baf2314b3ef4a2b97ef8899762f51fd4d1445115"},"schema_version":"1.0","source":{"id":"2501.03225","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03225","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03225v2","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03225","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"M7VCQ5V3ZG5X","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"M7VCQ5V3ZG5XDHR4","created_at":"2026-07-05T10:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"M7VCQ5V3","created_at":"2026-07-05T10:46:40Z"}],"graph_snapshots":[{"event_id":"sha256:cb1272f9d696361cdc084fc61b5e5424221ad9a5679ac2c024c68df64e86bb77","target":"graph","created_at":"2026-07-05T10:46:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.03225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T18:57:31Z","title":"Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03225","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b1e91c06c897c224da394f19be57055af18ccbeb3c211c6c321fb63b6cf011a7","target":"record","created_at":"2026-07-05T10:46:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3946cbfc0d72fad881d68d572a6f3888fd9b271117f5ce67b1a145036d128b80","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T18:57:31Z","title_canon_sha256":"43199180fbd6ee32aa4c4172baf2314b3ef4a2b97ef8899762f51fd4d1445115"},"schema_version":"1.0","source":{"id":"2501.03225","kind":"arxiv","version":2}},"canonical_sha256":"67ea2876bbc9bb719e3c97a07dadf414522b19723a67a59af927a00e23becf72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67ea2876bbc9bb719e3c97a07dadf414522b19723a67a59af927a00e23becf72","first_computed_at":"2026-07-05T10:46:40.432852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:40.432852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JljpVVSFjm+Uak6fH8WvvNerKeXcuVUN2viNQcmU9FUhdFUOyW6RywhLr8v5oyG7pDOMC5KRuMk6BHbEArd7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:40.433366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03225","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1e91c06c897c224da394f19be57055af18ccbeb3c211c6c321fb63b6cf011a7","sha256:cb1272f9d696361cdc084fc61b5e5424221ad9a5679ac2c024c68df64e86bb77"],"state_sha256":"51422bfd2de04bbcef7bd0375948cc101e00107f76e66d2fd5ed599911b9d092"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebxMpQfzcgYInWgwQEj4ViB8Carwopo/FKM4K7tNqsF+A+6VGYfC6RFLnxLYx4IrwfsoXKPkf3WnmNrve2ajDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:39:05.430198Z","bundle_sha256":"0d4d4d15f9f63e8d921ef2b160b8c006e041da338eb8875aef5db2354a135374"}}