{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QHXJND55S62ZCZUETTV27XSKKI","short_pith_number":"pith:QHXJND55","schema_version":"1.0","canonical_sha256":"81ee968fbd97b59166849cebafde4a522c69f51f0c8ea9c32e9f5e43c000005e","source":{"kind":"arxiv","id":"2504.04907","version":2},"attestation_state":"computed","paper":{"title":"Video-Bench: Human-Aligned Video Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chak Tou Leong, Chi Zhang, Hanwen Du, Hui Han, Jiaqi Chen, Jie Zhang, Junchen Fu, Li-Jia Li, Siyuan Li, Yiwen Yuan, Yongxin Ni, Youhua Li, Yuling Wu","submitted_at":"2025-04-07T10:32:42Z","abstract_excerpt":"Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories: traditional benchmarks, which use metrics and embeddings to evaluate generated video quality across multiple dimensions but often lack alignment with human judgments; and large language model (LLM)-based benchmarks, though capable of human-like reasoning, are constrained by a limited understanding of video quality metrics and cross-modal consistency. To address thes"},"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":"2504.04907","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T10:32:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76fc7aece4948c655b1c8b75bd12fbc54475ecd5187231f366ceb1083abcb482","abstract_canon_sha256":"fbb5aace0b596f7771a4bb51a8232cd2267497aecf5b1b2927abb8e97d04d4e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:33.704746Z","signature_b64":"RmhqMBcw8FoHNNb7DPWXv6Qxmu9RQvqT337oyx7JyvJYSO8MzunAZRGtniuVyvpKybS09V9pSUsIaIbnOw6NBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81ee968fbd97b59166849cebafde4a522c69f51f0c8ea9c32e9f5e43c000005e","last_reissued_at":"2026-07-05T10:55:33.704245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:33.704245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Bench: Human-Aligned Video Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chak Tou Leong, Chi Zhang, Hanwen Du, Hui Han, Jiaqi Chen, Jie Zhang, Junchen Fu, Li-Jia Li, Siyuan Li, Yiwen Yuan, Yongxin Ni, Youhua Li, Yuling Wu","submitted_at":"2025-04-07T10:32:42Z","abstract_excerpt":"Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories: traditional benchmarks, which use metrics and embeddings to evaluate generated video quality across multiple dimensions but often lack alignment with human judgments; and large language model (LLM)-based benchmarks, though capable of human-like reasoning, are constrained by a limited understanding of video quality metrics and cross-modal consistency. To address thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04907","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/2504.04907/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":"2504.04907","created_at":"2026-07-05T10:55:33.704301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04907v2","created_at":"2026-07-05T10:55:33.704301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04907","created_at":"2026-07-05T10:55:33.704301+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHXJND55S62Z","created_at":"2026-07-05T10:55:33.704301+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHXJND55S62ZCZUE","created_at":"2026-07-05T10:55:33.704301+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHXJND55","created_at":"2026-07-05T10:55:33.704301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08091","citing_title":"VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI","json":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI.json","graph_json":"https://pith.science/api/pith-number/QHXJND55S62ZCZUETTV27XSKKI/graph.json","events_json":"https://pith.science/api/pith-number/QHXJND55S62ZCZUETTV27XSKKI/events.json","paper":"https://pith.science/paper/QHXJND55"},"agent_actions":{"view_html":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI","download_json":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI.json","view_paper":"https://pith.science/paper/QHXJND55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04907&json=true","fetch_graph":"https://pith.science/api/pith-number/QHXJND55S62ZCZUETTV27XSKKI/graph.json","fetch_events":"https://pith.science/api/pith-number/QHXJND55S62ZCZUETTV27XSKKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI/action/storage_attestation","attest_author":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI/action/author_attestation","sign_citation":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI/action/citation_signature","submit_replication":"https://pith.science/pith/QHXJND55S62ZCZUETTV27XSKKI/action/replication_record"}},"created_at":"2026-07-05T10:55:33.704301+00:00","updated_at":"2026-07-05T10:55:33.704301+00:00"}