{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7767ZROVOL4ELE2FYYKLTCGCEH","short_pith_number":"pith:7767ZROV","schema_version":"1.0","canonical_sha256":"fffdfcc5d572f8459345c614b988c221c5392dae74056855c1f70667054f7459","source":{"kind":"arxiv","id":"2312.10628","version":2},"attestation_state":"computed","paper":{"title":"T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congyi Wang","submitted_at":"2023-12-17T06:58:31Z","abstract_excerpt":"In this study, we introduce T2M-HiFiGPT, a novel conditional generative framework for synthesizing human motion from textual descriptions. This framework is underpinned by a Residual Vector Quantized Variational AutoEncoder (RVQ-VAE) and a double-tier Generative Pretrained Transformer (GPT) architecture. We demonstrate that our CNN-based RVQ-VAE is capable of producing highly accurate 2D temporal-residual discrete motion representations. Our proposed double-tier GPT structure comprises a temporal GPT and a residual GPT. The temporal GPT efficiently condenses information from previous frames an"},"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":"2312.10628","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T06:58:31Z","cross_cats_sorted":[],"title_canon_sha256":"5840be791f93b2d4670b289e3a72797a4fb8b6112a3231d8160f9dd2c9507204","abstract_canon_sha256":"1061f92f363ccc694ecfdb000c27c02d67473c7b4a8f41c03eb09a9e2ea17103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:54.273044Z","signature_b64":"I53lXwCGeH3FmqXoRhG6jP/EvdydOGqUo4qUjBnxaO45RR08EpU1kgtJYPiWT3jXgwTF6IUUuOOVIl+59mInCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fffdfcc5d572f8459345c614b988c221c5392dae74056855c1f70667054f7459","last_reissued_at":"2026-07-05T07:27:54.272414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:54.272414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congyi Wang","submitted_at":"2023-12-17T06:58:31Z","abstract_excerpt":"In this study, we introduce T2M-HiFiGPT, a novel conditional generative framework for synthesizing human motion from textual descriptions. This framework is underpinned by a Residual Vector Quantized Variational AutoEncoder (RVQ-VAE) and a double-tier Generative Pretrained Transformer (GPT) architecture. We demonstrate that our CNN-based RVQ-VAE is capable of producing highly accurate 2D temporal-residual discrete motion representations. Our proposed double-tier GPT structure comprises a temporal GPT and a residual GPT. The temporal GPT efficiently condenses information from previous frames an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10628","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/2312.10628/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":"2312.10628","created_at":"2026-07-05T07:27:54.272476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10628v2","created_at":"2026-07-05T07:27:54.272476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10628","created_at":"2026-07-05T07:27:54.272476+00:00"},{"alias_kind":"pith_short_12","alias_value":"7767ZROVOL4E","created_at":"2026-07-05T07:27:54.272476+00:00"},{"alias_kind":"pith_short_16","alias_value":"7767ZROVOL4ELE2F","created_at":"2026-07-05T07:27:54.272476+00:00"},{"alias_kind":"pith_short_8","alias_value":"7767ZROV","created_at":"2026-07-05T07:27:54.272476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03191","citing_title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","ref_index":122,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH","json":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH.json","graph_json":"https://pith.science/api/pith-number/7767ZROVOL4ELE2FYYKLTCGCEH/graph.json","events_json":"https://pith.science/api/pith-number/7767ZROVOL4ELE2FYYKLTCGCEH/events.json","paper":"https://pith.science/paper/7767ZROV"},"agent_actions":{"view_html":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH","download_json":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH.json","view_paper":"https://pith.science/paper/7767ZROV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10628&json=true","fetch_graph":"https://pith.science/api/pith-number/7767ZROVOL4ELE2FYYKLTCGCEH/graph.json","fetch_events":"https://pith.science/api/pith-number/7767ZROVOL4ELE2FYYKLTCGCEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/action/storage_attestation","attest_author":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/action/author_attestation","sign_citation":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/action/citation_signature","submit_replication":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/action/replication_record"}},"created_at":"2026-07-05T07:27:54.272476+00:00","updated_at":"2026-07-05T07:27:54.272476+00:00"}