{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EU6RUSFSXBVYEDQNEH3ZMEAQHG","short_pith_number":"pith:EU6RUSFS","schema_version":"1.0","canonical_sha256":"253d1a48b2b86b820e0d21f796101039a0fa508574f9302630f2bf8fd1ea53bd","source":{"kind":"arxiv","id":"2411.16781","version":2},"attestation_state":"computed","paper":{"title":"UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen, Yiheng Li","submitted_at":"2024-11-25T08:06:30Z","abstract_excerpt":"Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a single modality of control signals and operate in isolation, limiting their application in real-world scenarios. This paper presents UniPose, a framework employing Large Language Models (LLMs) to comprehend, generate, and edit human poses across various modalities, including images, text, and 3D SMPL poses. Specifically, we apply a pose tokenizer to convert 3D poses into discrete pose tokens, enabling seamless integratio"},"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":"2411.16781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T08:06:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82c623cad1b7e285fa9d7497825f6dbec99395128f3dda6cfba6bfa694194b48","abstract_canon_sha256":"244b031f7c8286ff94e3b66a974e8487799a8addf1cdaa63842bc6a85ed53d9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:17.634828Z","signature_b64":"35MNShaA+lX+1JFZbkZNmYllAOvqWS2bT9hEJ8sAMxijcuEqYRR94MeyGGgK7yykSnhPTk112Sq3FL3AcZuZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"253d1a48b2b86b820e0d21f796101039a0fa508574f9302630f2bf8fd1ea53bd","last_reissued_at":"2026-07-05T10:41:17.634284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:17.634284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen, Yiheng Li","submitted_at":"2024-11-25T08:06:30Z","abstract_excerpt":"Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a single modality of control signals and operate in isolation, limiting their application in real-world scenarios. This paper presents UniPose, a framework employing Large Language Models (LLMs) to comprehend, generate, and edit human poses across various modalities, including images, text, and 3D SMPL poses. Specifically, we apply a pose tokenizer to convert 3D poses into discrete pose tokens, enabling seamless integratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16781","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/2411.16781/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":"2411.16781","created_at":"2026-07-05T10:41:17.634342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16781v2","created_at":"2026-07-05T10:41:17.634342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16781","created_at":"2026-07-05T10:41:17.634342+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU6RUSFSXBVY","created_at":"2026-07-05T10:41:17.634342+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU6RUSFSXBVYEDQN","created_at":"2026-07-05T10:41:17.634342+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU6RUSFS","created_at":"2026-07-05T10:41:17.634342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07863","citing_title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG","json":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG.json","graph_json":"https://pith.science/api/pith-number/EU6RUSFSXBVYEDQNEH3ZMEAQHG/graph.json","events_json":"https://pith.science/api/pith-number/EU6RUSFSXBVYEDQNEH3ZMEAQHG/events.json","paper":"https://pith.science/paper/EU6RUSFS"},"agent_actions":{"view_html":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG","download_json":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG.json","view_paper":"https://pith.science/paper/EU6RUSFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16781&json=true","fetch_graph":"https://pith.science/api/pith-number/EU6RUSFSXBVYEDQNEH3ZMEAQHG/graph.json","fetch_events":"https://pith.science/api/pith-number/EU6RUSFSXBVYEDQNEH3ZMEAQHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG/action/storage_attestation","attest_author":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG/action/author_attestation","sign_citation":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG/action/citation_signature","submit_replication":"https://pith.science/pith/EU6RUSFSXBVYEDQNEH3ZMEAQHG/action/replication_record"}},"created_at":"2026-07-05T10:41:17.634342+00:00","updated_at":"2026-07-05T10:41:17.634342+00:00"}