{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SEZSEW2MAJSZGGM2TPRVIFPF6Y","short_pith_number":"pith:SEZSEW2M","schema_version":"1.0","canonical_sha256":"9133225b4c026593199a9be35415e5f61d98d2da5bb4d724c1fc02471b84cc4a","source":{"kind":"arxiv","id":"2506.15483","version":1},"attestation_state":"computed","paper":{"title":"GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiyu Zhang, Shujia Li, Xinyuan Chen, Yaohui Wang, Yutong Ban","submitted_at":"2025-06-18T14:17:53Z","abstract_excerpt":"While diffusion models and large-scale motion datasets have advanced text-driven human motion synthesis, extending these advances to 4D human-object interaction (HOI) remains challenging, mainly due to the limited availability of large-scale 4D HOI datasets. In our study, we introduce GenHOI, a novel two-stage framework aimed at achieving two key objectives: 1) generalization to unseen objects and 2) the synthesis of high-fidelity 4D HOI sequences. In the initial stage of our framework, we employ an Object-AnchorNet to reconstruct sparse 3D HOI keyframes for unseen objects, learning solely fro"},"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":"2506.15483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-18T14:17:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0664b8e6f0fead5adc83c179991fd6cbc4c00fb4857776be8cd9e1209e6af5bc","abstract_canon_sha256":"b111bc24df16e5756f9a375bbe4e2d4a11cabaaa9f9aa49518bcebb5414641e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:44.508747Z","signature_b64":"Ce1sXVsd7xYb5yaYh23QIRIuZsLoMk71Da1x01I2HEjF1KIaWkKBbbx7n3lYkulhwLJmjwwPJNnT2EU0AOFRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9133225b4c026593199a9be35415e5f61d98d2da5bb4d724c1fc02471b84cc4a","last_reissued_at":"2026-07-05T11:23:44.508252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:44.508252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiyu Zhang, Shujia Li, Xinyuan Chen, Yaohui Wang, Yutong Ban","submitted_at":"2025-06-18T14:17:53Z","abstract_excerpt":"While diffusion models and large-scale motion datasets have advanced text-driven human motion synthesis, extending these advances to 4D human-object interaction (HOI) remains challenging, mainly due to the limited availability of large-scale 4D HOI datasets. In our study, we introduce GenHOI, a novel two-stage framework aimed at achieving two key objectives: 1) generalization to unseen objects and 2) the synthesis of high-fidelity 4D HOI sequences. In the initial stage of our framework, we employ an Object-AnchorNet to reconstruct sparse 3D HOI keyframes for unseen objects, learning solely fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15483","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/2506.15483/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":"2506.15483","created_at":"2026-07-05T11:23:44.508310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15483v1","created_at":"2026-07-05T11:23:44.508310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15483","created_at":"2026-07-05T11:23:44.508310+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEZSEW2MAJSZ","created_at":"2026-07-05T11:23:44.508310+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEZSEW2MAJSZGGM2","created_at":"2026-07-05T11:23:44.508310+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEZSEW2M","created_at":"2026-07-05T11:23:44.508310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22806","citing_title":"Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28215","citing_title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27491","citing_title":"Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04843","citing_title":"InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y","json":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y.json","graph_json":"https://pith.science/api/pith-number/SEZSEW2MAJSZGGM2TPRVIFPF6Y/graph.json","events_json":"https://pith.science/api/pith-number/SEZSEW2MAJSZGGM2TPRVIFPF6Y/events.json","paper":"https://pith.science/paper/SEZSEW2M"},"agent_actions":{"view_html":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y","download_json":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y.json","view_paper":"https://pith.science/paper/SEZSEW2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15483&json=true","fetch_graph":"https://pith.science/api/pith-number/SEZSEW2MAJSZGGM2TPRVIFPF6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/SEZSEW2MAJSZGGM2TPRVIFPF6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y/action/storage_attestation","attest_author":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y/action/author_attestation","sign_citation":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y/action/citation_signature","submit_replication":"https://pith.science/pith/SEZSEW2MAJSZGGM2TPRVIFPF6Y/action/replication_record"}},"created_at":"2026-07-05T11:23:44.508310+00:00","updated_at":"2026-07-05T11:23:44.508310+00:00"}