{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XUI2Z6Z3DVRT6YFSDL3XEJ63BW","short_pith_number":"pith:XUI2Z6Z3","schema_version":"1.0","canonical_sha256":"bd11acfb3b1d633f60b21af77227db0da1ebd4000dffa497bb709c4366c0c665","source":{"kind":"arxiv","id":"2505.20292","version":4},"attestation_state":"computed","paper":{"title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Lin, Jiebo Luo, Jinfa Huang, Li Yuan, Shenghai Yuan, Xianyi He, Yang Ye, Yufan Deng","submitted_at":"2025-05-26T17:59:46Z","abstract_excerpt":"Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose OpenS2V-Nexus, consisting of (i) OpenS2V-Eval, a fine-grained benchmark, and (ii) OpenS2V-5M, a million-scale dataset. In contrast to existing S2V benchmarks inherited from VBench that focus on global and coarse-grained assessment of generated videos, OpenS2V-Eval focuses on the model's ability to generate subject-consistent videos with natural subject appearance and iden"},"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":"2505.20292","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0c21bbad1b1fb359809ccae5df2726794b094c52185268dc92ab9d0ab9479e6","abstract_canon_sha256":"f1b0426a15f1606fbb573d907fdfb60258f857025adef5ed9a74777195d554cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:00.371216Z","signature_b64":"pPoEEUhqPYAkB28FSkl2nXuwb8nq9Ech6VIs5JzTG9KMSGVSnyxyss/GXDCmUDzmolIJzqh8BrGx+ben1PdbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd11acfb3b1d633f60b21af77227db0da1ebd4000dffa497bb709c4366c0c665","last_reissued_at":"2026-07-05T11:15:00.370729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:00.370729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Lin, Jiebo Luo, Jinfa Huang, Li Yuan, Shenghai Yuan, Xianyi He, Yang Ye, Yufan Deng","submitted_at":"2025-05-26T17:59:46Z","abstract_excerpt":"Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose OpenS2V-Nexus, consisting of (i) OpenS2V-Eval, a fine-grained benchmark, and (ii) OpenS2V-5M, a million-scale dataset. In contrast to existing S2V benchmarks inherited from VBench that focus on global and coarse-grained assessment of generated videos, OpenS2V-Eval focuses on the model's ability to generate subject-consistent videos with natural subject appearance and iden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20292","kind":"arxiv","version":4},"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/2505.20292/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":"2505.20292","created_at":"2026-07-05T11:15:00.370787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20292v4","created_at":"2026-07-05T11:15:00.370787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20292","created_at":"2026-07-05T11:15:00.370787+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUI2Z6Z3DVRT","created_at":"2026-07-05T11:15:00.370787+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUI2Z6Z3DVRT6YFS","created_at":"2026-07-05T11:15:00.370787+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUI2Z6Z3","created_at":"2026-07-05T11:15:00.370787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26058","citing_title":"DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10839","citing_title":"HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26628","citing_title":"Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00658","citing_title":"Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17488","citing_title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15199","citing_title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03147","citing_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23789","citing_title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23789","citing_title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17021","citing_title":"LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW","json":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW.json","graph_json":"https://pith.science/api/pith-number/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/graph.json","events_json":"https://pith.science/api/pith-number/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/events.json","paper":"https://pith.science/paper/XUI2Z6Z3"},"agent_actions":{"view_html":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW","download_json":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW.json","view_paper":"https://pith.science/paper/XUI2Z6Z3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20292&json=true","fetch_graph":"https://pith.science/api/pith-number/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/graph.json","fetch_events":"https://pith.science/api/pith-number/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/action/storage_attestation","attest_author":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/action/author_attestation","sign_citation":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/action/citation_signature","submit_replication":"https://pith.science/pith/XUI2Z6Z3DVRT6YFSDL3XEJ63BW/action/replication_record"}},"created_at":"2026-07-05T11:15:00.370787+00:00","updated_at":"2026-07-05T11:15:00.370787+00:00"}