{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CL7RAEMQ4EGHWQ4HT6UMGIV6A5","short_pith_number":"pith:CL7RAEMQ","schema_version":"1.0","canonical_sha256":"12ff101190e10c7b43879fa8c322be076c9c1e29dfcb4f2965669099dfcb42ce","source":{"kind":"arxiv","id":"2608.01942","version":1},"attestation_state":"computed","paper":{"title":"CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Zhu, Dong Ma, Wee Peng Tay, Xianjing Han, Yang Deng, Yuhan Su","submitted_at":"2026-08-03T09:16:06Z","abstract_excerpt":"Text-to-video (T2V) generation models have advanced rapidly, yet their ability to represent diverse cultural contexts remains underexplored. Existing benchmarks mainly focus on perceptual quality, physical plausibility, and text-video alignment, but do not directly assess whether generated videos capture culturally specific objects, actions, rituals, visible text, or audio cues. We introduce CultureVidBench, a comprehensive benchmark for evaluating cultural understanding in T2V generation. CultureVidBench contains 1,000 curated prompts covering 12 countries, 6 continents, 8 cultural regions, a"},"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":"2608.01942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T09:16:06Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"13bf79caf5bf1fd293e78c197a5259501caedd3ece3671e218130cb984e6b137","abstract_canon_sha256":"87b772a9bcf25e4dacd5100e323f21053cfbae81ae404cf18a477562ff9a31ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:12.674418Z","signature_b64":"CG3Bwegxe7BDW/+51LI3CBERxRmuJfiK7wDbCofgN3PuD2ZxnZ28VUJTBb+NufybY61nZ/wpT5cK9gktVNybAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ff101190e10c7b43879fa8c322be076c9c1e29dfcb4f2965669099dfcb42ce","last_reissued_at":"2026-08-04T02:10:12.672714Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:12.672714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Zhu, Dong Ma, Wee Peng Tay, Xianjing Han, Yang Deng, Yuhan Su","submitted_at":"2026-08-03T09:16:06Z","abstract_excerpt":"Text-to-video (T2V) generation models have advanced rapidly, yet their ability to represent diverse cultural contexts remains underexplored. Existing benchmarks mainly focus on perceptual quality, physical plausibility, and text-video alignment, but do not directly assess whether generated videos capture culturally specific objects, actions, rituals, visible text, or audio cues. We introduce CultureVidBench, a comprehensive benchmark for evaluating cultural understanding in T2V generation. CultureVidBench contains 1,000 curated prompts covering 12 countries, 6 continents, 8 cultural regions, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01942","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/2608.01942/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":"2608.01942","created_at":"2026-08-04T02:10:12.674258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01942v1","created_at":"2026-08-04T02:10:12.674258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01942","created_at":"2026-08-04T02:10:12.674258+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL7RAEMQ4EGH","created_at":"2026-08-04T02:10:12.674258+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL7RAEMQ4EGHWQ4H","created_at":"2026-08-04T02:10:12.674258+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL7RAEMQ","created_at":"2026-08-04T02:10:12.674258+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/CL7RAEMQ4EGHWQ4HT6UMGIV6A5","json":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5.json","graph_json":"https://pith.science/api/pith-number/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/graph.json","events_json":"https://pith.science/api/pith-number/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/events.json","paper":"https://pith.science/paper/CL7RAEMQ"},"agent_actions":{"view_html":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5","download_json":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5.json","view_paper":"https://pith.science/paper/CL7RAEMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01942&json=true","fetch_graph":"https://pith.science/api/pith-number/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/graph.json","fetch_events":"https://pith.science/api/pith-number/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/action/storage_attestation","attest_author":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/action/author_attestation","sign_citation":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/action/citation_signature","submit_replication":"https://pith.science/pith/CL7RAEMQ4EGHWQ4HT6UMGIV6A5/action/replication_record"}},"created_at":"2026-08-04T02:10:12.674258+00:00","updated_at":"2026-08-04T02:10:12.674258+00:00"}