{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QOFWCY46E2UODTJ24URBS37YNJ","short_pith_number":"pith:QOFWCY46","schema_version":"1.0","canonical_sha256":"838b61639e26a8e1cd3ae522196ff86a4a052145b0b5c8ad1b25a83763fc7c49","source":{"kind":"arxiv","id":"2503.19157","version":1},"attestation_state":"computed","paper":{"title":"HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bugra Tekin, Fu-Jen Chu, Hao Tang, Haoyu Ma, Hongfei Xue, Kevin J Liang, Kris Kitani, Matt Feiszli, Mingzhen Huang, Pierre Gleize, Siwei Lyu, Weiyao Wang, Xingyu Chen","submitted_at":"2025-03-24T21:25:29Z","abstract_excerpt":"We introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and generating high-quality 3D HOI sequences from a diverse range of conditional signals (\\eg text, objects, partial sequences). At its core, HOIGPT utilizes a large language model to predict the bidrectional transformation between HOI sequences and natural language descriptions. Given text inputs, HOIGPT generates a sequence of hand and object meshes; given (partial) HOI sequences, HOIGPT generates text descript"},"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":"2503.19157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T21:25:29Z","cross_cats_sorted":[],"title_canon_sha256":"85c042866e6202bb9b78c3d351acf66618d2f97f453d6bbbd6c20ac0629a8887","abstract_canon_sha256":"0cf90bb4dd08af16bdc7c45ba5e86422ae70c5c939e29e7da2ac0943807d8c33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:50.757936Z","signature_b64":"9MFxynbRr4ehXpqIq/OHWnhQcERZsqLPJ5/GNW7Cx8s3vSC/nkdWb+k0eVGTCt/QPuO7S5+PtAsX0vEB40x2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"838b61639e26a8e1cd3ae522196ff86a4a052145b0b5c8ad1b25a83763fc7c49","last_reissued_at":"2026-07-05T10:38:50.757499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:50.757499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bugra Tekin, Fu-Jen Chu, Hao Tang, Haoyu Ma, Hongfei Xue, Kevin J Liang, Kris Kitani, Matt Feiszli, Mingzhen Huang, Pierre Gleize, Siwei Lyu, Weiyao Wang, Xingyu Chen","submitted_at":"2025-03-24T21:25:29Z","abstract_excerpt":"We introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and generating high-quality 3D HOI sequences from a diverse range of conditional signals (\\eg text, objects, partial sequences). At its core, HOIGPT utilizes a large language model to predict the bidrectional transformation between HOI sequences and natural language descriptions. Given text inputs, HOIGPT generates a sequence of hand and object meshes; given (partial) HOI sequences, HOIGPT generates text descript"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19157","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/2503.19157/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":"2503.19157","created_at":"2026-07-05T10:38:50.757570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19157v1","created_at":"2026-07-05T10:38:50.757570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19157","created_at":"2026-07-05T10:38:50.757570+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOFWCY46E2UO","created_at":"2026-07-05T10:38:50.757570+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOFWCY46E2UODTJ2","created_at":"2026-07-05T10:38:50.757570+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOFWCY46","created_at":"2026-07-05T10:38:50.757570+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/QOFWCY46E2UODTJ24URBS37YNJ","json":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ.json","graph_json":"https://pith.science/api/pith-number/QOFWCY46E2UODTJ24URBS37YNJ/graph.json","events_json":"https://pith.science/api/pith-number/QOFWCY46E2UODTJ24URBS37YNJ/events.json","paper":"https://pith.science/paper/QOFWCY46"},"agent_actions":{"view_html":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ","download_json":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ.json","view_paper":"https://pith.science/paper/QOFWCY46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19157&json=true","fetch_graph":"https://pith.science/api/pith-number/QOFWCY46E2UODTJ24URBS37YNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QOFWCY46E2UODTJ24URBS37YNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ/action/storage_attestation","attest_author":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ/action/author_attestation","sign_citation":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ/action/citation_signature","submit_replication":"https://pith.science/pith/QOFWCY46E2UODTJ24URBS37YNJ/action/replication_record"}},"created_at":"2026-07-05T10:38:50.757570+00:00","updated_at":"2026-07-05T10:38:50.757570+00:00"}