{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OOLAVDRRDI3BBVMW5VKCMOCHBE","short_pith_number":"pith:OOLAVDRR","schema_version":"1.0","canonical_sha256":"73960a8e311a3610d596ed54263847093a45fa3b5599b00c1cbc44796b90790b","source":{"kind":"arxiv","id":"2506.08797","version":1},"attestation_state":"computed","paper":{"title":"HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Tang, Hongmei Wang, Juan Cao, Qinglin Lu, Qin Lin, Yi Chen, Yifeng Ma, Yuan Zhou, Zejing Rao, Zhiyong Xu, Zixiang Zhou, Ziyao Huang","submitted_at":"2025-06-10T13:45:00Z","abstract_excerpt":"To address key limitations in human-object interaction (HOI) video generation -- specifically the reliance on curated motion data, limited generalization to novel objects/scenarios, and restricted accessibility -- we introduce HunyuanVideo-HOMA, a weakly conditioned multimodal-driven framework. HunyuanVideo-HOMA enhances controllability and reduces dependency on precise inputs through sparse, decoupled motion guidance. It encodes appearance and motion signals into the dual input space of a multimodal diffusion transformer (MMDiT), fusing them within a shared context space to synthesize tempora"},"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":"2506.08797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T13:45:00Z","cross_cats_sorted":[],"title_canon_sha256":"6d362035fff2bd6100a90328277497438ade443461890ee2303dff0ef515288a","abstract_canon_sha256":"62ebff601bf2dea04a288cc8ea70197e8ea4b72eb3b0591ebd8212284c6133ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:13.403992Z","signature_b64":"rh4wtKfIcLaOojvpb87bjk+XUsj3tnQ2FWhdnygefmYAlWsKK+LeGtnYUEwuEXV55ueysH34wx+h5s730PzJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73960a8e311a3610d596ed54263847093a45fa3b5599b00c1cbc44796b90790b","last_reissued_at":"2026-07-05T11:19:13.403489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:13.403489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Tang, Hongmei Wang, Juan Cao, Qinglin Lu, Qin Lin, Yi Chen, Yifeng Ma, Yuan Zhou, Zejing Rao, Zhiyong Xu, Zixiang Zhou, Ziyao Huang","submitted_at":"2025-06-10T13:45:00Z","abstract_excerpt":"To address key limitations in human-object interaction (HOI) video generation -- specifically the reliance on curated motion data, limited generalization to novel objects/scenarios, and restricted accessibility -- we introduce HunyuanVideo-HOMA, a weakly conditioned multimodal-driven framework. HunyuanVideo-HOMA enhances controllability and reduces dependency on precise inputs through sparse, decoupled motion guidance. It encodes appearance and motion signals into the dual input space of a multimodal diffusion transformer (MMDiT), fusing them within a shared context space to synthesize tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08797","kind":"arxiv","version":1},"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/2506.08797/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":"2506.08797","created_at":"2026-07-05T11:19:13.403546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08797v1","created_at":"2026-07-05T11:19:13.403546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08797","created_at":"2026-07-05T11:19:13.403546+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOLAVDRRDI3B","created_at":"2026-07-05T11:19:13.403546+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOLAVDRRDI3BBVMW","created_at":"2026-07-05T11:19:13.403546+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOLAVDRR","created_at":"2026-07-05T11:19:13.403546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2512.09646","citing_title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE","json":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE.json","graph_json":"https://pith.science/api/pith-number/OOLAVDRRDI3BBVMW5VKCMOCHBE/graph.json","events_json":"https://pith.science/api/pith-number/OOLAVDRRDI3BBVMW5VKCMOCHBE/events.json","paper":"https://pith.science/paper/OOLAVDRR"},"agent_actions":{"view_html":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE","download_json":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE.json","view_paper":"https://pith.science/paper/OOLAVDRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08797&json=true","fetch_graph":"https://pith.science/api/pith-number/OOLAVDRRDI3BBVMW5VKCMOCHBE/graph.json","fetch_events":"https://pith.science/api/pith-number/OOLAVDRRDI3BBVMW5VKCMOCHBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE/action/storage_attestation","attest_author":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE/action/author_attestation","sign_citation":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE/action/citation_signature","submit_replication":"https://pith.science/pith/OOLAVDRRDI3BBVMW5VKCMOCHBE/action/replication_record"}},"created_at":"2026-07-05T11:19:13.403546+00:00","updated_at":"2026-07-05T11:19:13.403546+00:00"}