{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5IJBCQQOOJ5MIYDFPBO6QOH5EE","short_pith_number":"pith:5IJBCQQO","schema_version":"1.0","canonical_sha256":"ea1211420e727ac46065785de838fd210c3e99cec6420363aabb12f32ae5d4b8","source":{"kind":"arxiv","id":"2411.19786","version":1},"attestation_state":"computed","paper":{"title":"MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Xu, Kecheng Zheng, Wei Ji, Yiming Wu, Zicheng Wang","submitted_at":"2024-11-29T15:48:24Z","abstract_excerpt":"Recently, human motion analysis has experienced great improvement due to inspiring generative models such as the denoising diffusion model and large language model. While the existing approaches mainly focus on generating motions with textual descriptions and overlook the reciprocal task. In this paper, we present~\\textbf{MoTe}, a unified multi-modal model that could handle diverse tasks by learning the marginal, conditional, and joint distributions of motion and text simultaneously. MoTe enables us to handle the paired text-motion generation, motion captioning, and text-driven motion generati"},"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":"2411.19786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T15:48:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ec1e234d5614c9e2c87d4bee89e86a417dbfe2ca8de678df28e76168f6d67e51","abstract_canon_sha256":"ee8b5d23c48a757a6a7a410303d7605bf29465e3684da30ee7add770f9a15361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:08.020222Z","signature_b64":"eQjvtGVSZ03HMHQ9wlOy4/pTXOwpKdbXmHWfEdWB3ti1KRWw1TyMMgzisBrqwVkH/s/ur0dUcK/BuBOEVNacDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea1211420e727ac46065785de838fd210c3e99cec6420363aabb12f32ae5d4b8","last_reissued_at":"2026-07-05T09:42:08.019806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:08.019806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Xu, Kecheng Zheng, Wei Ji, Yiming Wu, Zicheng Wang","submitted_at":"2024-11-29T15:48:24Z","abstract_excerpt":"Recently, human motion analysis has experienced great improvement due to inspiring generative models such as the denoising diffusion model and large language model. While the existing approaches mainly focus on generating motions with textual descriptions and overlook the reciprocal task. In this paper, we present~\\textbf{MoTe}, a unified multi-modal model that could handle diverse tasks by learning the marginal, conditional, and joint distributions of motion and text simultaneously. MoTe enables us to handle the paired text-motion generation, motion captioning, and text-driven motion generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19786","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/2411.19786/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":"2411.19786","created_at":"2026-07-05T09:42:08.019869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19786v1","created_at":"2026-07-05T09:42:08.019869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19786","created_at":"2026-07-05T09:42:08.019869+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IJBCQQOOJ5M","created_at":"2026-07-05T09:42:08.019869+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IJBCQQOOJ5MIYDF","created_at":"2026-07-05T09:42:08.019869+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IJBCQQO","created_at":"2026-07-05T09:42:08.019869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12370","citing_title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21668","citing_title":"Encoder-Free Human Motion Understanding via Structured Motion Descriptions","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE","json":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE.json","graph_json":"https://pith.science/api/pith-number/5IJBCQQOOJ5MIYDFPBO6QOH5EE/graph.json","events_json":"https://pith.science/api/pith-number/5IJBCQQOOJ5MIYDFPBO6QOH5EE/events.json","paper":"https://pith.science/paper/5IJBCQQO"},"agent_actions":{"view_html":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE","download_json":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE.json","view_paper":"https://pith.science/paper/5IJBCQQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19786&json=true","fetch_graph":"https://pith.science/api/pith-number/5IJBCQQOOJ5MIYDFPBO6QOH5EE/graph.json","fetch_events":"https://pith.science/api/pith-number/5IJBCQQOOJ5MIYDFPBO6QOH5EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE/action/storage_attestation","attest_author":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE/action/author_attestation","sign_citation":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE/action/citation_signature","submit_replication":"https://pith.science/pith/5IJBCQQOOJ5MIYDFPBO6QOH5EE/action/replication_record"}},"created_at":"2026-07-05T09:42:08.019869+00:00","updated_at":"2026-07-05T09:42:08.019869+00:00"}