{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KSDZPWOWESI2RFAXLAYGBUH445","short_pith_number":"pith:KSDZPWOW","schema_version":"1.0","canonical_sha256":"548797d9d62491a89417583060d0fce77f34ec881d1a2aa2ce01c89aab45b10b","source":{"kind":"arxiv","id":"2606.11805","version":1},"attestation_state":"computed","paper":{"title":"TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Zhencun Jiang, Zixiong Hao","submitted_at":"2026-06-10T08:38:40Z","abstract_excerpt":"Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the output must preserve language semantics, cross-view consistency, object geometry, articulated hand shape, and physically plausible contact. We present TextHOI-3D, a staged framework that uses generated multi-view observations as an explicit interface between text-conditioned visual generation and geometry-aware hand-object recovery. TextHOI-3D learns a compact VQ token space for fixed-camera hand-object observations, predicts multi-view visual tokens "},"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":"2606.11805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T08:38:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82dba3e2991cedfdcd738022d8c990f33c1b7a0498dcbf977be845043bccdee8","abstract_canon_sha256":"a143dfa4f238010e6dddcfab38fb74775ed68ad057357b8815aeda797050847b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:09.027378Z","signature_b64":"ZYeGRnhPVaPNzS7IdjhqWaL2X1g3eL22RvMq7/KQ+73TcloJHufJQiNfAMCwpqhxDDDu+C3MEOnw+SGHmsj8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548797d9d62491a89417583060d0fce77f34ec881d1a2aa2ce01c89aab45b10b","last_reissued_at":"2026-06-11T01:10:09.026431Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:09.026431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Zhencun Jiang, Zixiong Hao","submitted_at":"2026-06-10T08:38:40Z","abstract_excerpt":"Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the output must preserve language semantics, cross-view consistency, object geometry, articulated hand shape, and physically plausible contact. We present TextHOI-3D, a staged framework that uses generated multi-view observations as an explicit interface between text-conditioned visual generation and geometry-aware hand-object recovery. TextHOI-3D learns a compact VQ token space for fixed-camera hand-object observations, predicts multi-view visual tokens "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11805","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/2606.11805/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":"2606.11805","created_at":"2026-06-11T01:10:09.026599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11805v1","created_at":"2026-06-11T01:10:09.026599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11805","created_at":"2026-06-11T01:10:09.026599+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSDZPWOWESI2","created_at":"2026-06-11T01:10:09.026599+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSDZPWOWESI2RFAX","created_at":"2026-06-11T01:10:09.026599+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSDZPWOW","created_at":"2026-06-11T01:10:09.026599+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/KSDZPWOWESI2RFAXLAYGBUH445","json":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445.json","graph_json":"https://pith.science/api/pith-number/KSDZPWOWESI2RFAXLAYGBUH445/graph.json","events_json":"https://pith.science/api/pith-number/KSDZPWOWESI2RFAXLAYGBUH445/events.json","paper":"https://pith.science/paper/KSDZPWOW"},"agent_actions":{"view_html":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445","download_json":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445.json","view_paper":"https://pith.science/paper/KSDZPWOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11805&json=true","fetch_graph":"https://pith.science/api/pith-number/KSDZPWOWESI2RFAXLAYGBUH445/graph.json","fetch_events":"https://pith.science/api/pith-number/KSDZPWOWESI2RFAXLAYGBUH445/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445/action/storage_attestation","attest_author":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445/action/author_attestation","sign_citation":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445/action/citation_signature","submit_replication":"https://pith.science/pith/KSDZPWOWESI2RFAXLAYGBUH445/action/replication_record"}},"created_at":"2026-06-11T01:10:09.026599+00:00","updated_at":"2026-06-11T01:10:09.026599+00:00"}