{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XSSBR3XI6BFHSS2FMNRA4NENS2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8b4e159f0904521134cc53ffe4f703c6d48272ad5bcb8dfc5969da4eaec5057e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-15T09:34:42Z","title_canon_sha256":"9e0da44bba50a9d8b2e8b65bfb2f468c279109c72459eb2217ce20f63e17e129"},"schema_version":"1.0","source":{"id":"2301.06052","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.06052","created_at":"2026-07-05T06:53:33Z"},{"alias_kind":"arxiv_version","alias_value":"2301.06052v4","created_at":"2026-07-05T06:53:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06052","created_at":"2026-07-05T06:53:33Z"},{"alias_kind":"pith_short_12","alias_value":"XSSBR3XI6BFH","created_at":"2026-07-05T06:53:33Z"},{"alias_kind":"pith_short_16","alias_value":"XSSBR3XI6BFHSS2F","created_at":"2026-07-05T06:53:33Z"},{"alias_kind":"pith_short_8","alias_value":"XSSBR3XI","created_at":"2026-07-05T06:53:33Z"}],"graph_snapshots":[{"event_id":"sha256:cfd236da3fea43f29bff414d94704cc7ff37c5500bbdd1f81a1679026f021617","target":"graph","created_at":"2026-07-05T06:53:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.06052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongtao Lu, Hongwei Zhao, Jianrong Zhang, Shaoli Huang, Xiaodong Cun, Xi Shen, Yangsong Zhang, Yong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-15T09:34:42Z","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06052","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6da7fb9e6a1fce9dd7a6411f604a49388d2d6c12de25bc7ffb29095c39298344","target":"record","created_at":"2026-07-05T06:53:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8b4e159f0904521134cc53ffe4f703c6d48272ad5bcb8dfc5969da4eaec5057e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-15T09:34:42Z","title_canon_sha256":"9e0da44bba50a9d8b2e8b65bfb2f468c279109c72459eb2217ce20f63e17e129"},"schema_version":"1.0","source":{"id":"2301.06052","kind":"arxiv","version":4}},"canonical_sha256":"bca418eee8f04a794b4563620e348d969dcab7c18c24569ae2a7e04502ff588f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bca418eee8f04a794b4563620e348d969dcab7c18c24569ae2a7e04502ff588f","first_computed_at":"2026-07-05T06:53:33.456594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:33.456594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L4TxgugdzmlPD+7t6wt2zpFYmeSunVlnwK2VVMLp9WWhdCMeE9zJ2KG+noioKdapMOt/YoWItCX4mllo1fMaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:33.457173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.06052","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6da7fb9e6a1fce9dd7a6411f604a49388d2d6c12de25bc7ffb29095c39298344","sha256:cfd236da3fea43f29bff414d94704cc7ff37c5500bbdd1f81a1679026f021617"],"state_sha256":"91aa1eea24a7cc382a70e5e2ed1b6482c438c5dc32eb765474e909ac9e729fc9"}