{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RYKAFCULZSW6IH2JAT5JFTCPHO","short_pith_number":"pith:RYKAFCUL","schema_version":"1.0","canonical_sha256":"8e14028a8bccade41f4904fa92cc4f3b8e1a69c7814588559cf823664c8578a8","source":{"kind":"arxiv","id":"2502.11079","version":2},"attestation_state":"computed","paper":{"title":"Phantom: Subject-consistent video generation via cross-modal alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingchuan Li, Gen Li, Jiawei Liu, Lijie Liu, Qian He, Siyu Zhou, Tianxiang Ma, Xinglong Wu, Zhuowei Chen","submitted_at":"2025-02-16T11:02:50Z","abstract_excerpt":"The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage. We refer to this as Subject-to-Video, which extracts subject elements from reference images and generates subject-consistent videos following textual instructions. We believe that the essence of subject-to-video lies in balancing the dual-modal prompts of text and image, thereby deeply and simultaneously aligning both text and visual content. To this end, we propose Phantom, a unified video generation framework fo"},"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":"2502.11079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-16T11:02:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc9860b94424b14fb04763cccc5e9511da92164cd609092b66a95e082bf57ed1","abstract_canon_sha256":"3d0bffa2828b8e733c0907bb017a0620cb06dd5577892af13cc1059ecc877815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:00.748382Z","signature_b64":"5LNPCRU5KkPowK5N48A9x4InC5FmTslXSbqGBbiGMCMyViObzXZu7ui7XfDOBdGQkBhav+P8xXYc6hqkvU+wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e14028a8bccade41f4904fa92cc4f3b8e1a69c7814588559cf823664c8578a8","last_reissued_at":"2026-07-05T10:47:00.747845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:00.747845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phantom: Subject-consistent video generation via cross-modal alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingchuan Li, Gen Li, Jiawei Liu, Lijie Liu, Qian He, Siyu Zhou, Tianxiang Ma, Xinglong Wu, Zhuowei Chen","submitted_at":"2025-02-16T11:02:50Z","abstract_excerpt":"The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage. We refer to this as Subject-to-Video, which extracts subject elements from reference images and generates subject-consistent videos following textual instructions. We believe that the essence of subject-to-video lies in balancing the dual-modal prompts of text and image, thereby deeply and simultaneously aligning both text and visual content. To this end, we propose Phantom, a unified video generation framework fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11079","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/2502.11079/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":"2502.11079","created_at":"2026-07-05T10:47:00.747912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11079v2","created_at":"2026-07-05T10:47:00.747912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11079","created_at":"2026-07-05T10:47:00.747912+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYKAFCULZSW6","created_at":"2026-07-05T10:47:00.747912+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYKAFCULZSW6IH2J","created_at":"2026-07-05T10:47:00.747912+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYKAFCUL","created_at":"2026-07-05T10:47:00.747912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20799","citing_title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11670","citing_title":"ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10839","citing_title":"HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07508","citing_title":"Streaming Video Generation with Streaming Force Control","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02753","citing_title":"MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28531","citing_title":"A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23610","citing_title":"EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22940","citing_title":"One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04702","citing_title":"FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19720","citing_title":"ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11244","citing_title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10030","citing_title":"Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04934","citing_title":"Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO","json":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO.json","graph_json":"https://pith.science/api/pith-number/RYKAFCULZSW6IH2JAT5JFTCPHO/graph.json","events_json":"https://pith.science/api/pith-number/RYKAFCULZSW6IH2JAT5JFTCPHO/events.json","paper":"https://pith.science/paper/RYKAFCUL"},"agent_actions":{"view_html":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO","download_json":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO.json","view_paper":"https://pith.science/paper/RYKAFCUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11079&json=true","fetch_graph":"https://pith.science/api/pith-number/RYKAFCULZSW6IH2JAT5JFTCPHO/graph.json","fetch_events":"https://pith.science/api/pith-number/RYKAFCULZSW6IH2JAT5JFTCPHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO/action/storage_attestation","attest_author":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO/action/author_attestation","sign_citation":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO/action/citation_signature","submit_replication":"https://pith.science/pith/RYKAFCULZSW6IH2JAT5JFTCPHO/action/replication_record"}},"created_at":"2026-07-05T10:47:00.747912+00:00","updated_at":"2026-07-05T10:47:00.747912+00:00"}