{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:APUXNAOCD2VXHB7OKOCGNYFQ34","short_pith_number":"pith:APUXNAOC","schema_version":"1.0","canonical_sha256":"03e97681c21eab7387ee538466e0b0df10121b6931278dff10a299f8d4a10cbe","source":{"kind":"arxiv","id":"2407.14505","version":2},"attestation_state":"computed","paper":{"title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyi Huang, Kaiyue Sun, Xian Liu, Xihui Liu, Yue Wu, Zhenguo Li, Zihan Xu","submitted_at":"2024-07-19T17:58:36Z","abstract_excerpt":"Text-to-video (T2V) generative models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this important ability for evaluation. In this work, we conduct the first systematic study on compositional text-to-video generation. We propose T2V-CompBench, the first benchmark tailored for compositional text-to-video generation. T2V-CompBench encompasses diverse aspects of compositionality, including consistent attribute binding, dynamic attribute binding, spatial r"},"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":"2407.14505","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T17:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"7e94fafce2743815ef4008bc488d2c5cf0ba225ee75481106afad7ad4c13db91","abstract_canon_sha256":"c5ff999a59513c91db2cfdef4dc896250727e70774c49ebba1da1683d1fe3528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:15.069378Z","signature_b64":"LVii1bi9vsmTFJiOiKDM3UA6QoEWX4X4kluZSOw6VU7xkg5nfUJ3KYQloMz23Iz04+s3rOv12k7H+d7DI4eJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e97681c21eab7387ee538466e0b0df10121b6931278dff10a299f8d4a10cbe","last_reissued_at":"2026-07-05T10:01:15.068872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:15.068872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyi Huang, Kaiyue Sun, Xian Liu, Xihui Liu, Yue Wu, Zhenguo Li, Zihan Xu","submitted_at":"2024-07-19T17:58:36Z","abstract_excerpt":"Text-to-video (T2V) generative models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this important ability for evaluation. In this work, we conduct the first systematic study on compositional text-to-video generation. We propose T2V-CompBench, the first benchmark tailored for compositional text-to-video generation. T2V-CompBench encompasses diverse aspects of compositionality, including consistent attribute binding, dynamic attribute binding, spatial r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14505","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/2407.14505/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":"2407.14505","created_at":"2026-07-05T10:01:15.068936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14505v2","created_at":"2026-07-05T10:01:15.068936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14505","created_at":"2026-07-05T10:01:15.068936+00:00"},{"alias_kind":"pith_short_12","alias_value":"APUXNAOCD2VX","created_at":"2026-07-05T10:01:15.068936+00:00"},{"alias_kind":"pith_short_16","alias_value":"APUXNAOCD2VXHB7O","created_at":"2026-07-05T10:01:15.068936+00:00"},{"alias_kind":"pith_short_8","alias_value":"APUXNAOC","created_at":"2026-07-05T10:01:15.068936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26769","citing_title":"ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31026","citing_title":"OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29360","citing_title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01481","citing_title":"SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15115","citing_title":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17180","citing_title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05363","citing_title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20206","citing_title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05635","citing_title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15185","citing_title":"Quantitative Video World Model Evaluation for Geometric-Consistency","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14269","citing_title":"PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34","json":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34.json","graph_json":"https://pith.science/api/pith-number/APUXNAOCD2VXHB7OKOCGNYFQ34/graph.json","events_json":"https://pith.science/api/pith-number/APUXNAOCD2VXHB7OKOCGNYFQ34/events.json","paper":"https://pith.science/paper/APUXNAOC"},"agent_actions":{"view_html":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34","download_json":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34.json","view_paper":"https://pith.science/paper/APUXNAOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14505&json=true","fetch_graph":"https://pith.science/api/pith-number/APUXNAOCD2VXHB7OKOCGNYFQ34/graph.json","fetch_events":"https://pith.science/api/pith-number/APUXNAOCD2VXHB7OKOCGNYFQ34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34/action/storage_attestation","attest_author":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34/action/author_attestation","sign_citation":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34/action/citation_signature","submit_replication":"https://pith.science/pith/APUXNAOCD2VXHB7OKOCGNYFQ34/action/replication_record"}},"created_at":"2026-07-05T10:01:15.068936+00:00","updated_at":"2026-07-05T10:01:15.068936+00:00"}