{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GAJ57S6RP7NC7EZAQQ2DEZRCEC","short_pith_number":"pith:GAJ57S6R","schema_version":"1.0","canonical_sha256":"3013dfcbd17fda2f9320843432662220a520b0477cf6152c5fa1598c9c7a21f8","source":{"kind":"arxiv","id":"2501.05098","version":1},"attestation_state":"computed","paper":{"title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Guanlin Wu, Haoqian Wang, Jing Lin, Lei Zhang, Ruimao Zhang, Shunlin Lu, Yuanhao Cai, Yuhong Zhang, Yurong Fu","submitted_at":"2025-01-09T09:37:27Z","abstract_excerpt":"In this paper, we introduce Motion-X++, a large-scale multimodal 3D expressive whole-body human motion dataset. Existing motion datasets predominantly capture body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions, and are typically limited to lab settings with manually labeled text descriptions, thereby restricting their scalability. To address this issue, we develop a scalable annotation pipeline that can automatically capture 3D whole-body human motion and comprehensive textural labels from RGB videos and build the Motion-X dataset comprising 81.1K te"},"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":"2501.05098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T09:37:27Z","cross_cats_sorted":[],"title_canon_sha256":"ee92b93e9741e472d7e4fa1992a0549a81eff6794dc9644a4c320f768bdd7660","abstract_canon_sha256":"4c3defcea7afc4ceaf19a1d30f3ed744daef7910610e267c49c9cbebc7d3294b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:04.319625Z","signature_b64":"jSzxfKQKiP1mRGQFztyx8sm4FI/QZQbhTl2P+ehoKPMgy2HxdIRXRtfEYNKCy2fB0NZ1UMd9vwhz62xRqukWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3013dfcbd17fda2f9320843432662220a520b0477cf6152c5fa1598c9c7a21f8","last_reissued_at":"2026-07-05T09:59:04.319193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:04.319193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Guanlin Wu, Haoqian Wang, Jing Lin, Lei Zhang, Ruimao Zhang, Shunlin Lu, Yuanhao Cai, Yuhong Zhang, Yurong Fu","submitted_at":"2025-01-09T09:37:27Z","abstract_excerpt":"In this paper, we introduce Motion-X++, a large-scale multimodal 3D expressive whole-body human motion dataset. Existing motion datasets predominantly capture body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions, and are typically limited to lab settings with manually labeled text descriptions, thereby restricting their scalability. To address this issue, we develop a scalable annotation pipeline that can automatically capture 3D whole-body human motion and comprehensive textural labels from RGB videos and build the Motion-X dataset comprising 81.1K te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05098","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/2501.05098/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":"2501.05098","created_at":"2026-07-05T09:59:04.319255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05098v1","created_at":"2026-07-05T09:59:04.319255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05098","created_at":"2026-07-05T09:59:04.319255+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAJ57S6RP7NC","created_at":"2026-07-05T09:59:04.319255+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAJ57S6RP7NC7EZA","created_at":"2026-07-05T09:59:04.319255+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAJ57S6R","created_at":"2026-07-05T09:59:04.319255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05243","citing_title":"GUSH3R: Everyone Everywhere All at Once as Gaussians","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26981","citing_title":"In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20888","citing_title":"Fine-grained Human Motion Understanding with Language Models","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12153","citing_title":"TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10340","citing_title":"OMG: Omni-Modal Motion Generation for Generalist Humanoid Control","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06953","citing_title":"LIMMT: Less is More for Motion Tracking","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03985","citing_title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27547","citing_title":"Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29488","citing_title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22894","citing_title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25361","citing_title":"HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC","json":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC.json","graph_json":"https://pith.science/api/pith-number/GAJ57S6RP7NC7EZAQQ2DEZRCEC/graph.json","events_json":"https://pith.science/api/pith-number/GAJ57S6RP7NC7EZAQQ2DEZRCEC/events.json","paper":"https://pith.science/paper/GAJ57S6R"},"agent_actions":{"view_html":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC","download_json":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC.json","view_paper":"https://pith.science/paper/GAJ57S6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05098&json=true","fetch_graph":"https://pith.science/api/pith-number/GAJ57S6RP7NC7EZAQQ2DEZRCEC/graph.json","fetch_events":"https://pith.science/api/pith-number/GAJ57S6RP7NC7EZAQQ2DEZRCEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC/action/storage_attestation","attest_author":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC/action/author_attestation","sign_citation":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC/action/citation_signature","submit_replication":"https://pith.science/pith/GAJ57S6RP7NC7EZAQQ2DEZRCEC/action/replication_record"}},"created_at":"2026-07-05T09:59:04.319255+00:00","updated_at":"2026-07-05T09:59:04.319255+00:00"}