{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQPU7LPONGEKALJFNFACQHWUAG","short_pith_number":"pith:MQPU7LPO","schema_version":"1.0","canonical_sha256":"641f4fadee6988a02d256940281ed401a8aa24d09b3bfbbef98a2509a26537bd","source":{"kind":"arxiv","id":"2412.18600","version":2},"attestation_state":"computed","paper":{"title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Hongjie Li, Hong-Xing Yu, Jiajun Wu, Jiaman Li","submitted_at":"2024-12-24T18:55:38Z","abstract_excerpt":"Human-scene interaction (HSI) generation is crucial for applications in embodied AI, virtual reality, and robotics. Yet, existing methods cannot synthesize interactions in unseen environments such as in-the-wild scenes or reconstructed scenes, as they rely on paired 3D scenes and captured human motion data for training, which are unavailable for unseen environments. We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis, eliminating the need for training on any MoCap data. Our key insight is to distill human-scene interactions from state-of-the-art vid"},"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":"2412.18600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:55:38Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"cfd280c7a8f236d3fbe74361829a6eb0d58267faf1da45d654c47ee4d06a5450","abstract_canon_sha256":"e2bcc36618bd21d10dd511d03713d316353b61d2508513975e566e2e9b2c27ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:33.620110Z","signature_b64":"eRBeMkE1UDEUynfd3Xat73sZaTy3NgHNyl+xSKMim5albk5d7SpA1sqPINfxm6RvRgRk7TODsqqKke+7eB8JBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641f4fadee6988a02d256940281ed401a8aa24d09b3bfbbef98a2509a26537bd","last_reissued_at":"2026-07-05T10:36:33.619092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:33.619092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Hongjie Li, Hong-Xing Yu, Jiajun Wu, Jiaman Li","submitted_at":"2024-12-24T18:55:38Z","abstract_excerpt":"Human-scene interaction (HSI) generation is crucial for applications in embodied AI, virtual reality, and robotics. Yet, existing methods cannot synthesize interactions in unseen environments such as in-the-wild scenes or reconstructed scenes, as they rely on paired 3D scenes and captured human motion data for training, which are unavailable for unseen environments. We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis, eliminating the need for training on any MoCap data. Our key insight is to distill human-scene interactions from state-of-the-art vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18600","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/2412.18600/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":"2412.18600","created_at":"2026-07-05T10:36:33.619207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18600v2","created_at":"2026-07-05T10:36:33.619207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18600","created_at":"2026-07-05T10:36:33.619207+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQPU7LPONGEK","created_at":"2026-07-05T10:36:33.619207+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQPU7LPONGEKALJF","created_at":"2026-07-05T10:36:33.619207+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQPU7LPO","created_at":"2026-07-05T10:36:33.619207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09646","citing_title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","ref_index":40,"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":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14953","citing_title":"Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG","json":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG.json","graph_json":"https://pith.science/api/pith-number/MQPU7LPONGEKALJFNFACQHWUAG/graph.json","events_json":"https://pith.science/api/pith-number/MQPU7LPONGEKALJFNFACQHWUAG/events.json","paper":"https://pith.science/paper/MQPU7LPO"},"agent_actions":{"view_html":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG","download_json":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG.json","view_paper":"https://pith.science/paper/MQPU7LPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18600&json=true","fetch_graph":"https://pith.science/api/pith-number/MQPU7LPONGEKALJFNFACQHWUAG/graph.json","fetch_events":"https://pith.science/api/pith-number/MQPU7LPONGEKALJFNFACQHWUAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG/action/storage_attestation","attest_author":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG/action/author_attestation","sign_citation":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG/action/citation_signature","submit_replication":"https://pith.science/pith/MQPU7LPONGEKALJFNFACQHWUAG/action/replication_record"}},"created_at":"2026-07-05T10:36:33.619207+00:00","updated_at":"2026-07-05T10:36:33.619207+00:00"}