{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSSBR3XI6BFHSS2FMNRA4NENS2","short_pith_number":"pith:XSSBR3XI","schema_version":"1.0","canonical_sha256":"bca418eee8f04a794b4563620e348d969dcab7c18c24569ae2a7e04502ff588f","source":{"kind":"arxiv","id":"2301.06052","version":4},"attestation_state":"computed","paper":{"title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongtao Lu, Hongwei Zhao, Jianrong Zhang, Shaoli Huang, Xiaodong Cun, Xi Shen, Yangsong Zhang, Yong Zhang","submitted_at":"2023-01-15T09:34:42Z","abstract_excerpt":"In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive appro"},"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":"2301.06052","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-15T09:34:42Z","cross_cats_sorted":[],"title_canon_sha256":"9e0da44bba50a9d8b2e8b65bfb2f468c279109c72459eb2217ce20f63e17e129","abstract_canon_sha256":"8b4e159f0904521134cc53ffe4f703c6d48272ad5bcb8dfc5969da4eaec5057e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:33.457173Z","signature_b64":"L4TxgugdzmlPD+7t6wt2zpFYmeSunVlnwK2VVMLp9WWhdCMeE9zJ2KG+noioKdapMOt/YoWItCX4mllo1fMaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bca418eee8f04a794b4563620e348d969dcab7c18c24569ae2a7e04502ff588f","last_reissued_at":"2026-07-05T06:53:33.456594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:33.456594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongtao Lu, Hongwei Zhao, Jianrong Zhang, Shaoli Huang, Xiaodong Cun, Xi Shen, Yangsong Zhang, Yong Zhang","submitted_at":"2023-01-15T09:34:42Z","abstract_excerpt":"In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06052","kind":"arxiv","version":4},"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/2301.06052/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":"2301.06052","created_at":"2026-07-05T06:53:33.456655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06052v4","created_at":"2026-07-05T06:53:33.456655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06052","created_at":"2026-07-05T06:53:33.456655+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSSBR3XI6BFH","created_at":"2026-07-05T06:53:33.456655+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSSBR3XI6BFHSS2F","created_at":"2026-07-05T06:53:33.456655+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSSBR3XI","created_at":"2026-07-05T06:53:33.456655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26879","citing_title":"Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29488","citing_title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14202","citing_title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11704","citing_title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10466","citing_title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2","json":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2.json","graph_json":"https://pith.science/api/pith-number/XSSBR3XI6BFHSS2FMNRA4NENS2/graph.json","events_json":"https://pith.science/api/pith-number/XSSBR3XI6BFHSS2FMNRA4NENS2/events.json","paper":"https://pith.science/paper/XSSBR3XI"},"agent_actions":{"view_html":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2","download_json":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2.json","view_paper":"https://pith.science/paper/XSSBR3XI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06052&json=true","fetch_graph":"https://pith.science/api/pith-number/XSSBR3XI6BFHSS2FMNRA4NENS2/graph.json","fetch_events":"https://pith.science/api/pith-number/XSSBR3XI6BFHSS2FMNRA4NENS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2/action/storage_attestation","attest_author":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2/action/author_attestation","sign_citation":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2/action/citation_signature","submit_replication":"https://pith.science/pith/XSSBR3XI6BFHSS2FMNRA4NENS2/action/replication_record"}},"created_at":"2026-07-05T06:53:33.456655+00:00","updated_at":"2026-07-05T06:53:33.456655+00:00"}