{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6MWN3ELSMXJWSEUQJNMU5GLOSP","short_pith_number":"pith:6MWN3ELS","schema_version":"1.0","canonical_sha256":"f32cdd917265d36912904b594e996e93cbc11105b4026074a56e33ee9e61c884","source":{"kind":"arxiv","id":"2509.14232","version":5},"attestation_state":"computed","paper":{"title":"GenExam: A Multidisciplinary Text-to-Image Exam","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Gen Luo, Jifeng Dai, Penghao Yin, Wenhai Wang, Xiangyu Zhao, Yu Qiao, Zhaokai Wang","submitted_at":"2025-09-17T17:59:14Z","abstract_excerpt":"Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style benchmarks mainly focus on understanding and reasoning tasks, and current generation benchmarks emphasize the illustration of world knowledge and visual concepts, neglecting the evaluation of rigorous drawing exams. We introduce GenExam, the first benchmark for multidisciplinary text-to-image exams, featuring 1,000 samples across 10 subjects with exam-style prompts organized under a four-level taxonomy. Each problem is equipped with ground-truth images "},"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":"2509.14232","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-17T17:59:14Z","cross_cats_sorted":[],"title_canon_sha256":"ba615ee5354a890e083e3e36c92ba579d7d98df4574c10d83f52c86059cd4992","abstract_canon_sha256":"3b48e9576cf562bd20e2e59f83e5304ec02f5f0f4d12e83e0379e4607543806f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:17.487810Z","signature_b64":"Q0qG7Ci1B2bwY8bpa3Ge8NOyDv/WGO0+CEcyO/f5HTCKr262WvRA55EJAGPkpQXf5pfBn52RXYF3aJKM6xohCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f32cdd917265d36912904b594e996e93cbc11105b4026074a56e33ee9e61c884","last_reissued_at":"2026-05-17T23:39:17.487078Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:17.487078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenExam: A Multidisciplinary Text-to-Image Exam","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Gen Luo, Jifeng Dai, Penghao Yin, Wenhai Wang, Xiangyu Zhao, Yu Qiao, Zhaokai Wang","submitted_at":"2025-09-17T17:59:14Z","abstract_excerpt":"Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style benchmarks mainly focus on understanding and reasoning tasks, and current generation benchmarks emphasize the illustration of world knowledge and visual concepts, neglecting the evaluation of rigorous drawing exams. We introduce GenExam, the first benchmark for multidisciplinary text-to-image exams, featuring 1,000 samples across 10 subjects with exam-style prompts organized under a four-level taxonomy. Each problem is equipped with ground-truth images "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14232","kind":"arxiv","version":5},"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":"2509.14232","created_at":"2026-05-17T23:39:17.487187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.14232v5","created_at":"2026-05-17T23:39:17.487187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14232","created_at":"2026-05-17T23:39:17.487187+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MWN3ELSMXJW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MWN3ELSMXJWSEUQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MWN3ELS","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2602.06663","citing_title":"PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01070","citing_title":"How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08163","citing_title":"MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP","json":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP.json","graph_json":"https://pith.science/api/pith-number/6MWN3ELSMXJWSEUQJNMU5GLOSP/graph.json","events_json":"https://pith.science/api/pith-number/6MWN3ELSMXJWSEUQJNMU5GLOSP/events.json","paper":"https://pith.science/paper/6MWN3ELS"},"agent_actions":{"view_html":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP","download_json":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP.json","view_paper":"https://pith.science/paper/6MWN3ELS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.14232&json=true","fetch_graph":"https://pith.science/api/pith-number/6MWN3ELSMXJWSEUQJNMU5GLOSP/graph.json","fetch_events":"https://pith.science/api/pith-number/6MWN3ELSMXJWSEUQJNMU5GLOSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP/action/storage_attestation","attest_author":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP/action/author_attestation","sign_citation":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP/action/citation_signature","submit_replication":"https://pith.science/pith/6MWN3ELSMXJWSEUQJNMU5GLOSP/action/replication_record"}},"created_at":"2026-05-17T23:39:17.487187+00:00","updated_at":"2026-05-17T23:39:17.487187+00:00"}