{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UBBHENJ6HVBHWGYLLRBYBYRFMF","short_pith_number":"pith:UBBHENJ6","schema_version":"1.0","canonical_sha256":"a04272353e3d427b1b0b5c4380e225615a91602ede76205d0c5983ab374d521b","source":{"kind":"arxiv","id":"2506.10568","version":2},"attestation_state":"computed","paper":{"title":"DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lizhen Wang, Mingyuan Gao, Ming Zhou, Pengfei Wei, Pengrui Wang, Tianshu Hu, Yuan Zhang, Zerong Zheng, Zhurong Xia","submitted_at":"2025-06-12T10:58:23Z","abstract_excerpt":"In e-commerce and digital marketing, generating high-fidelity human-product demonstration videos is important for effective product presentation. However, most existing frameworks either fail to preserve the identities of both humans and products or lack an understanding of human-product spatial relationships, leading to unrealistic representations and unnatural interactions. To address these challenges, we propose a Diffusion Transformer (DiT)-based framework. Our method simultaneously preserves human identities and product-specific details, such as logos and textures, by injecting paired hum"},"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":"2506.10568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T10:58:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc873620555522da2ebcdd0685ac9ebaab652a3712c723611f8c030770e6bdd4","abstract_canon_sha256":"8bf858cc22926eccf4de1abe69ded239e56da895b85c3d5f1f236c73af713104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:02.213051Z","signature_b64":"/5pwZXmMkxuLiA1HTxKRIGemUcK8ZLEcEeb2ImeMAmcmQQvAJQiAL/3gxSQVjdgiTXBiOv082kFXTHs3krrlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04272353e3d427b1b0b5c4380e225615a91602ede76205d0c5983ab374d521b","last_reissued_at":"2026-07-05T12:00:02.212546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:02.212546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lizhen Wang, Mingyuan Gao, Ming Zhou, Pengfei Wei, Pengrui Wang, Tianshu Hu, Yuan Zhang, Zerong Zheng, Zhurong Xia","submitted_at":"2025-06-12T10:58:23Z","abstract_excerpt":"In e-commerce and digital marketing, generating high-fidelity human-product demonstration videos is important for effective product presentation. However, most existing frameworks either fail to preserve the identities of both humans and products or lack an understanding of human-product spatial relationships, leading to unrealistic representations and unnatural interactions. To address these challenges, we propose a Diffusion Transformer (DiT)-based framework. Our method simultaneously preserves human identities and product-specific details, such as logos and textures, by injecting paired hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10568","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/2506.10568/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":"2506.10568","created_at":"2026-07-05T12:00:02.212604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10568v2","created_at":"2026-07-05T12:00:02.212604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10568","created_at":"2026-07-05T12:00:02.212604+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBBHENJ6HVBH","created_at":"2026-07-05T12:00:02.212604+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBBHENJ6HVBHWGYL","created_at":"2026-07-05T12:00:02.212604+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBBHENJ6","created_at":"2026-07-05T12:00:02.212604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19636","citing_title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF","json":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF.json","graph_json":"https://pith.science/api/pith-number/UBBHENJ6HVBHWGYLLRBYBYRFMF/graph.json","events_json":"https://pith.science/api/pith-number/UBBHENJ6HVBHWGYLLRBYBYRFMF/events.json","paper":"https://pith.science/paper/UBBHENJ6"},"agent_actions":{"view_html":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF","download_json":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF.json","view_paper":"https://pith.science/paper/UBBHENJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10568&json=true","fetch_graph":"https://pith.science/api/pith-number/UBBHENJ6HVBHWGYLLRBYBYRFMF/graph.json","fetch_events":"https://pith.science/api/pith-number/UBBHENJ6HVBHWGYLLRBYBYRFMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF/action/storage_attestation","attest_author":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF/action/author_attestation","sign_citation":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF/action/citation_signature","submit_replication":"https://pith.science/pith/UBBHENJ6HVBHWGYLLRBYBYRFMF/action/replication_record"}},"created_at":"2026-07-05T12:00:02.212604+00:00","updated_at":"2026-07-05T12:00:02.212604+00:00"}