{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UUXDPA3U54OVFQJ4SBIPQ64N3T","short_pith_number":"pith:UUXDPA3U","schema_version":"1.0","canonical_sha256":"a52e378374ef1d52c13c9050f87b8ddcf54db09cc5c770c8f40c9aedfe9e5f19","source":{"kind":"arxiv","id":"2505.04946","version":1},"attestation_state":"computed","paper":{"title":"T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahao Zhang, Jiale Zhao, Jiayan Huo, Xuyang Guo, Zhao Song, Zhenmei Shi","submitted_at":"2025-05-08T04:49:52Z","abstract_excerpt":"Thanks to recent advancements in scalable deep architectures and large-scale pretraining, text-to-video generation has achieved unprecedented capabilities in producing high-fidelity, instruction-following content across a wide range of styles, enabling applications in advertising, entertainment, and education. However, these models' ability to render precise on-screen text, such as captions or mathematical formulas, remains largely untested, posing significant challenges for applications requiring exact textual accuracy. In this work, we introduce T2VTextBench, the first human-evaluation bench"},"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":"2505.04946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T04:49:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"19d250674c448dc6156f4995759df41ffc1f8b0fa87f5a97ef0cc38b0c659162","abstract_canon_sha256":"d7f687735b2f006e226ddcba1406f06f5f6228ad92092a4646ea49973b12ff2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:16.444485Z","signature_b64":"pf5CmEazh353SbI+FUjDoN8R8e7N9Vo2k2GL2+PfT+UGULZLSNPfm3fiSGeVYh9UHS3W29qaTE8nDzvsH9zwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a52e378374ef1d52c13c9050f87b8ddcf54db09cc5c770c8f40c9aedfe9e5f19","last_reissued_at":"2026-07-05T11:00:16.443925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:16.443925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahao Zhang, Jiale Zhao, Jiayan Huo, Xuyang Guo, Zhao Song, Zhenmei Shi","submitted_at":"2025-05-08T04:49:52Z","abstract_excerpt":"Thanks to recent advancements in scalable deep architectures and large-scale pretraining, text-to-video generation has achieved unprecedented capabilities in producing high-fidelity, instruction-following content across a wide range of styles, enabling applications in advertising, entertainment, and education. However, these models' ability to render precise on-screen text, such as captions or mathematical formulas, remains largely untested, posing significant challenges for applications requiring exact textual accuracy. In this work, we introduce T2VTextBench, the first human-evaluation bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04946","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/2505.04946/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":"2505.04946","created_at":"2026-07-05T11:00:16.443988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04946v1","created_at":"2026-07-05T11:00:16.443988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04946","created_at":"2026-07-05T11:00:16.443988+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUXDPA3U54OV","created_at":"2026-07-05T11:00:16.443988+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUXDPA3U54OVFQJ4","created_at":"2026-07-05T11:00:16.443988+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUXDPA3U","created_at":"2026-07-05T11:00:16.443988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09639","citing_title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T","json":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T.json","graph_json":"https://pith.science/api/pith-number/UUXDPA3U54OVFQJ4SBIPQ64N3T/graph.json","events_json":"https://pith.science/api/pith-number/UUXDPA3U54OVFQJ4SBIPQ64N3T/events.json","paper":"https://pith.science/paper/UUXDPA3U"},"agent_actions":{"view_html":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T","download_json":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T.json","view_paper":"https://pith.science/paper/UUXDPA3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04946&json=true","fetch_graph":"https://pith.science/api/pith-number/UUXDPA3U54OVFQJ4SBIPQ64N3T/graph.json","fetch_events":"https://pith.science/api/pith-number/UUXDPA3U54OVFQJ4SBIPQ64N3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T/action/storage_attestation","attest_author":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T/action/author_attestation","sign_citation":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T/action/citation_signature","submit_replication":"https://pith.science/pith/UUXDPA3U54OVFQJ4SBIPQ64N3T/action/replication_record"}},"created_at":"2026-07-05T11:00:16.443988+00:00","updated_at":"2026-07-05T11:00:16.443988+00:00"}