{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VNYKIIEWTV6D4Q2SRNU5GIIUZL","short_pith_number":"pith:VNYKIIEW","schema_version":"1.0","canonical_sha256":"ab70a420969d7c3e43528b69d32114cae0565c28cc03d22a958e127d015aa6c2","source":{"kind":"arxiv","id":"2608.01905","version":1},"attestation_state":"computed","paper":{"title":"PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Zhang, Wei Min, Yebin Liu, Zhenhao Zhang","submitted_at":"2026-08-03T08:39:31Z","abstract_excerpt":"Hand-object interaction (HOI) is a fundamental human behavior with broad applications in AR/VR, digital humans, and embodied interaction. Existing methods typically require predefined object geometry, object trajectories, or task-specific conditions, limiting their use with natural real-world inputs. To address this, we study a more practical problem of synthesizing 3D hand-object interaction sequences from a single RGB photograph and an open-vocabulary language instruction, and introduce PhotoHOI. PhotoHOI first uses a vision-language model to parse the input image and instruction into a stru"},"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":"2608.01905","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T08:39:31Z","cross_cats_sorted":[],"title_canon_sha256":"641bdf27e6d100dfe2493b75eb9e86e25c5807f55dd418ad3feec7b517cfb390","abstract_canon_sha256":"b9619ea8bfeff69d7dab927b9f629b49a4f3d38d3624f5264d5d83343e205a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:07:36.220563Z","signature_b64":"jhQSA6Ised47cp1SVAi6HL7KvuNMYdJg/yjZJAQFOO+Oo9O2tuGRF0/oapxfQoqTBVzqU4AE2oB9ykfG081wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab70a420969d7c3e43528b69d32114cae0565c28cc03d22a958e127d015aa6c2","last_reissued_at":"2026-08-04T02:07:36.218968Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:07:36.218968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Zhang, Wei Min, Yebin Liu, Zhenhao Zhang","submitted_at":"2026-08-03T08:39:31Z","abstract_excerpt":"Hand-object interaction (HOI) is a fundamental human behavior with broad applications in AR/VR, digital humans, and embodied interaction. Existing methods typically require predefined object geometry, object trajectories, or task-specific conditions, limiting their use with natural real-world inputs. To address this, we study a more practical problem of synthesizing 3D hand-object interaction sequences from a single RGB photograph and an open-vocabulary language instruction, and introduce PhotoHOI. PhotoHOI first uses a vision-language model to parse the input image and instruction into a stru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01905","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/2608.01905/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":"2608.01905","created_at":"2026-08-04T02:07:36.220512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01905v1","created_at":"2026-08-04T02:07:36.220512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01905","created_at":"2026-08-04T02:07:36.220512+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNYKIIEWTV6D","created_at":"2026-08-04T02:07:36.220512+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNYKIIEWTV6D4Q2S","created_at":"2026-08-04T02:07:36.220512+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNYKIIEW","created_at":"2026-08-04T02:07:36.220512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL","json":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL.json","graph_json":"https://pith.science/api/pith-number/VNYKIIEWTV6D4Q2SRNU5GIIUZL/graph.json","events_json":"https://pith.science/api/pith-number/VNYKIIEWTV6D4Q2SRNU5GIIUZL/events.json","paper":"https://pith.science/paper/VNYKIIEW"},"agent_actions":{"view_html":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL","download_json":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL.json","view_paper":"https://pith.science/paper/VNYKIIEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01905&json=true","fetch_graph":"https://pith.science/api/pith-number/VNYKIIEWTV6D4Q2SRNU5GIIUZL/graph.json","fetch_events":"https://pith.science/api/pith-number/VNYKIIEWTV6D4Q2SRNU5GIIUZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL/action/storage_attestation","attest_author":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL/action/author_attestation","sign_citation":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL/action/citation_signature","submit_replication":"https://pith.science/pith/VNYKIIEWTV6D4Q2SRNU5GIIUZL/action/replication_record"}},"created_at":"2026-08-04T02:07:36.220512+00:00","updated_at":"2026-08-04T02:07:36.220512+00:00"}