{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4J35BWZRQAGDYMSZURDFG4MR4C","short_pith_number":"pith:4J35BWZR","schema_version":"1.0","canonical_sha256":"e277d0db31800c3c3259a446537191e0b922e5e718cb9410633354cd3c996e09","source":{"kind":"arxiv","id":"2501.08333","version":3},"attestation_state":"computed","paper":{"title":"DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanbyul Joo, Hyeonwoo Kim, Sangwon Baik","submitted_at":"2025-01-14T18:59:59Z","abstract_excerpt":"Modeling how humans interact with objects is crucial for AI to effectively assist or mimic human behaviors. Existing studies for learning such ability primarily focus on static human-object interaction (HOI) patterns, such as contact and spatial relationships, while dynamic HOI patterns, capturing the movement of humans and objects over time, remain relatively underexplored. In this paper, we present a novel framework for learning Dynamic Affordance across various target object categories. To address the scarcity of 4D HOI datasets, our method learns the 3D dynamic affordance from syntheticall"},"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":"2501.08333","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"e8ab7b679f271a802d09f864dd78104b60c3c4ceb615d34038bae3894e57724b","abstract_canon_sha256":"ef4d8c678d9d309030c4c411d6a6f5d2b64a76d86921a0f178e7613844076495"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:20.957638Z","signature_b64":"Rrtu90u4szo2Iabh6SjrRJk3VLmasq/pnLfRO+UTeWt8BiG4u28tNf/aKpfK+bD0lQoXK3ODIDl101G7OSB6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e277d0db31800c3c3259a446537191e0b922e5e718cb9410633354cd3c996e09","last_reissued_at":"2026-07-05T11:51:20.957140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:20.957140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanbyul Joo, Hyeonwoo Kim, Sangwon Baik","submitted_at":"2025-01-14T18:59:59Z","abstract_excerpt":"Modeling how humans interact with objects is crucial for AI to effectively assist or mimic human behaviors. Existing studies for learning such ability primarily focus on static human-object interaction (HOI) patterns, such as contact and spatial relationships, while dynamic HOI patterns, capturing the movement of humans and objects over time, remain relatively underexplored. In this paper, we present a novel framework for learning Dynamic Affordance across various target object categories. To address the scarcity of 4D HOI datasets, our method learns the 3D dynamic affordance from syntheticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08333","kind":"arxiv","version":3},"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/2501.08333/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":"2501.08333","created_at":"2026-07-05T11:51:20.957198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08333v3","created_at":"2026-07-05T11:51:20.957198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08333","created_at":"2026-07-05T11:51:20.957198+00:00"},{"alias_kind":"pith_short_12","alias_value":"4J35BWZRQAGD","created_at":"2026-07-05T11:51:20.957198+00:00"},{"alias_kind":"pith_short_16","alias_value":"4J35BWZRQAGDYMSZ","created_at":"2026-07-05T11:51:20.957198+00:00"},{"alias_kind":"pith_short_8","alias_value":"4J35BWZR","created_at":"2026-07-05T11:51:20.957198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C","json":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C.json","graph_json":"https://pith.science/api/pith-number/4J35BWZRQAGDYMSZURDFG4MR4C/graph.json","events_json":"https://pith.science/api/pith-number/4J35BWZRQAGDYMSZURDFG4MR4C/events.json","paper":"https://pith.science/paper/4J35BWZR"},"agent_actions":{"view_html":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C","download_json":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C.json","view_paper":"https://pith.science/paper/4J35BWZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08333&json=true","fetch_graph":"https://pith.science/api/pith-number/4J35BWZRQAGDYMSZURDFG4MR4C/graph.json","fetch_events":"https://pith.science/api/pith-number/4J35BWZRQAGDYMSZURDFG4MR4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C/action/storage_attestation","attest_author":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C/action/author_attestation","sign_citation":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C/action/citation_signature","submit_replication":"https://pith.science/pith/4J35BWZRQAGDYMSZURDFG4MR4C/action/replication_record"}},"created_at":"2026-07-05T11:51:20.957198+00:00","updated_at":"2026-07-05T11:51:20.957198+00:00"}