{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UWVT5RTXKTN6Z5PFFDTEZXCY4Z","short_pith_number":"pith:UWVT5RTX","schema_version":"1.0","canonical_sha256":"a5ab3ec67754dbecf5e528e64cdc58e6621a9115a87ddc98cfa3179259fe40ca","source":{"kind":"arxiv","id":"2606.01285","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-Intensive Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxu Wang, Mingda Chen","submitted_at":"2026-05-31T15:11:07Z","abstract_excerpt":"Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-intensive video generation (KIVI), where models generate videos from short information-seeking prompts that ask for explanations, procedures, or demonstrations. To evaluate this setting, we construct KIVI-Bench, a benchmark of 1,080 prompts, and propose automatic metrics for factuality and helpfulness. Human evaluation shows that our metrics significantly better align with human annotations than existing alternatives. Experiments on seven "},"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":"2606.01285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T15:11:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9a05f1b88dcfbd0d1aacb04c640aaea1b2b1f6ac64a0ce5a4bc679f0f9b8dd5","abstract_canon_sha256":"a8bfecd8b2b958b4420e875b65c95d32d12dc7af1dc0bcb0359cb1476c521ea3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:28.918817Z","signature_b64":"aL7mbWZUIOao1dlgPLCkIS95n41kYBn5rYiN/iJThLNJxWcMaaeJsGaFFTNKjm3Pg+N/iMJMYcuec6E4yeIuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5ab3ec67754dbecf5e528e64cdc58e6621a9115a87ddc98cfa3179259fe40ca","last_reissued_at":"2026-06-02T02:04:28.918340Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:28.918340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Intensive Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxu Wang, Mingda Chen","submitted_at":"2026-05-31T15:11:07Z","abstract_excerpt":"Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-intensive video generation (KIVI), where models generate videos from short information-seeking prompts that ask for explanations, procedures, or demonstrations. To evaluate this setting, we construct KIVI-Bench, a benchmark of 1,080 prompts, and propose automatic metrics for factuality and helpfulness. Human evaluation shows that our metrics significantly better align with human annotations than existing alternatives. Experiments on seven "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01285","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/2606.01285/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":"2606.01285","created_at":"2026-06-02T02:04:28.918395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01285v1","created_at":"2026-06-02T02:04:28.918395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01285","created_at":"2026-06-02T02:04:28.918395+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWVT5RTXKTN6","created_at":"2026-06-02T02:04:28.918395+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWVT5RTXKTN6Z5PF","created_at":"2026-06-02T02:04:28.918395+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWVT5RTX","created_at":"2026-06-02T02:04:28.918395+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/UWVT5RTXKTN6Z5PFFDTEZXCY4Z","json":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z.json","graph_json":"https://pith.science/api/pith-number/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/graph.json","events_json":"https://pith.science/api/pith-number/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/events.json","paper":"https://pith.science/paper/UWVT5RTX"},"agent_actions":{"view_html":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z","download_json":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z.json","view_paper":"https://pith.science/paper/UWVT5RTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01285&json=true","fetch_graph":"https://pith.science/api/pith-number/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/action/storage_attestation","attest_author":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/action/author_attestation","sign_citation":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/action/citation_signature","submit_replication":"https://pith.science/pith/UWVT5RTXKTN6Z5PFFDTEZXCY4Z/action/replication_record"}},"created_at":"2026-06-02T02:04:28.918395+00:00","updated_at":"2026-06-02T02:04:28.918395+00:00"}