{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CU7MP3CZZC6WSH3F4PK6Y6RBKF","short_pith_number":"pith:CU7MP3CZ","schema_version":"1.0","canonical_sha256":"153ec7ec59c8bd691f65e3d5ec7a215168441d2d83220c10cbb6a142a7fed444","source":{"kind":"arxiv","id":"2510.26412","version":3},"attestation_state":"computed","paper":{"title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengyue Wu, Kehai Chen, Min Zhang, Xiangqing Zheng","submitted_at":"2025-10-30T12:00:46Z","abstract_excerpt":"Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under complex textual inputs remains a significant challenge. In response to this challenge, we present LoCoT2V-Bench, a benchmark for long video generation (LVG) featuring multi-scene prompts with hierarchical metadata (e.g., character settings and camera behaviors), constructed from collected real-world videos. We further propose LoCoT2V-Eval, a multi-dimensional framework covering perceptual quality, text-video alignment, temporal quality, dynamic quality, and"},"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":"2510.26412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-30T12:00:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc78ec1877887e9359bf321c772332d952d11b44bc810778bb6ca59d57763e97","abstract_canon_sha256":"90df70cce09ae928ffe735e3d946b22294ccf341be2993d41465760c070edd07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:57.593231Z","signature_b64":"N09h7QRy0xlYCKHWsV98DMpLApWgne9pGGiAXXq5SKeDt6j09+WejHON1a/Z7ezT3sfuRMkJNn2wCcItQaHmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153ec7ec59c8bd691f65e3d5ec7a215168441d2d83220c10cbb6a142a7fed444","last_reissued_at":"2026-05-29T01:04:57.592657Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:57.592657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengyue Wu, Kehai Chen, Min Zhang, Xiangqing Zheng","submitted_at":"2025-10-30T12:00:46Z","abstract_excerpt":"Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under complex textual inputs remains a significant challenge. In response to this challenge, we present LoCoT2V-Bench, a benchmark for long video generation (LVG) featuring multi-scene prompts with hierarchical metadata (e.g., character settings and camera behaviors), constructed from collected real-world videos. We further propose LoCoT2V-Eval, a multi-dimensional framework covering perceptual quality, text-video alignment, temporal quality, dynamic quality, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.26412","kind":"arxiv","version":3},"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/2510.26412/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":"2510.26412","created_at":"2026-05-29T01:04:57.592743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.26412v3","created_at":"2026-05-29T01:04:57.592743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.26412","created_at":"2026-05-29T01:04:57.592743+00:00"},{"alias_kind":"pith_short_12","alias_value":"CU7MP3CZZC6W","created_at":"2026-05-29T01:04:57.592743+00:00"},{"alias_kind":"pith_short_16","alias_value":"CU7MP3CZZC6WSH3F","created_at":"2026-05-29T01:04:57.592743+00:00"},{"alias_kind":"pith_short_8","alias_value":"CU7MP3CZ","created_at":"2026-05-29T01:04:57.592743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.07823","citing_title":"LPM 1.0: Video-based Character Performance Model","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17982","citing_title":"Mitigating Multimodal Hallucination via Phase-wise Self-reward","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17428","citing_title":"Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF","json":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF.json","graph_json":"https://pith.science/api/pith-number/CU7MP3CZZC6WSH3F4PK6Y6RBKF/graph.json","events_json":"https://pith.science/api/pith-number/CU7MP3CZZC6WSH3F4PK6Y6RBKF/events.json","paper":"https://pith.science/paper/CU7MP3CZ"},"agent_actions":{"view_html":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF","download_json":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF.json","view_paper":"https://pith.science/paper/CU7MP3CZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.26412&json=true","fetch_graph":"https://pith.science/api/pith-number/CU7MP3CZZC6WSH3F4PK6Y6RBKF/graph.json","fetch_events":"https://pith.science/api/pith-number/CU7MP3CZZC6WSH3F4PK6Y6RBKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF/action/storage_attestation","attest_author":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF/action/author_attestation","sign_citation":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF/action/citation_signature","submit_replication":"https://pith.science/pith/CU7MP3CZZC6WSH3F4PK6Y6RBKF/action/replication_record"}},"created_at":"2026-05-29T01:04:57.592743+00:00","updated_at":"2026-05-29T01:04:57.592743+00:00"}