{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QTV7VY7ESVV3FOPFOA6TUILKED","short_pith_number":"pith:QTV7VY7E","schema_version":"1.0","canonical_sha256":"84ebfae3e4956bb2b9e5703d3a216a20e5b2045239dfb83b4c8c2cfb356941fb","source":{"kind":"arxiv","id":"2311.18836","version":2},"attestation_state":"computed","paper":{"title":"ChatPose: Chatting about 3D Human Pose","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Lin, Michael J. Black, Priyanka Patel, Sai Kumar Dwivedi, Yao Feng, Yu Sun","submitted_at":"2023-11-30T18:59:52Z","abstract_excerpt":"We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description, a process that intertwines image interpretation, world knowledge, and an understanding of body language. Traditional human pose estimation and generation methods often operate in isolation, lacking semantic understanding and reasoning abilities. ChatPose addresses these limitations by embedding SMPL poses as distinct si"},"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":"2311.18836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"e58fbfc126ef217ff347b936550a10644bffa5ffd71ea648f98c6f0b5c93678a","abstract_canon_sha256":"d5a1e6574fbec2fdef3fc45564f0cede9eab647176ef9e768d7369ea1c8faf75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:21.914793Z","signature_b64":"hSaZtU+pk+58d8Ez0Fuwv+gTtZ6vLG8ate8JKxfiqqFBJr9Pp+LgcsZpw6zCmEHrAAioKku0uhPD2szeYtK/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ebfae3e4956bb2b9e5703d3a216a20e5b2045239dfb83b4c8c2cfb356941fb","last_reissued_at":"2026-07-05T08:11:21.914220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:21.914220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatPose: Chatting about 3D Human Pose","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Lin, Michael J. Black, Priyanka Patel, Sai Kumar Dwivedi, Yao Feng, Yu Sun","submitted_at":"2023-11-30T18:59:52Z","abstract_excerpt":"We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description, a process that intertwines image interpretation, world knowledge, and an understanding of body language. Traditional human pose estimation and generation methods often operate in isolation, lacking semantic understanding and reasoning abilities. ChatPose addresses these limitations by embedding SMPL poses as distinct si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18836","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/2311.18836/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":"2311.18836","created_at":"2026-07-05T08:11:21.914278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18836v2","created_at":"2026-07-05T08:11:21.914278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18836","created_at":"2026-07-05T08:11:21.914278+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTV7VY7ESVV3","created_at":"2026-07-05T08:11:21.914278+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTV7VY7ESVV3FOPF","created_at":"2026-07-05T08:11:21.914278+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTV7VY7E","created_at":"2026-07-05T08:11:21.914278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14643","citing_title":"RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED","json":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED.json","graph_json":"https://pith.science/api/pith-number/QTV7VY7ESVV3FOPFOA6TUILKED/graph.json","events_json":"https://pith.science/api/pith-number/QTV7VY7ESVV3FOPFOA6TUILKED/events.json","paper":"https://pith.science/paper/QTV7VY7E"},"agent_actions":{"view_html":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED","download_json":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED.json","view_paper":"https://pith.science/paper/QTV7VY7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18836&json=true","fetch_graph":"https://pith.science/api/pith-number/QTV7VY7ESVV3FOPFOA6TUILKED/graph.json","fetch_events":"https://pith.science/api/pith-number/QTV7VY7ESVV3FOPFOA6TUILKED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED/action/storage_attestation","attest_author":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED/action/author_attestation","sign_citation":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED/action/citation_signature","submit_replication":"https://pith.science/pith/QTV7VY7ESVV3FOPFOA6TUILKED/action/replication_record"}},"created_at":"2026-07-05T08:11:21.914278+00:00","updated_at":"2026-07-05T08:11:21.914278+00:00"}