{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7767ZROVOL4ELE2FYYKLTCGCEH","short_pith_number":"pith:7767ZROV","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"},"canonical_sha256":"fffdfcc5d572f8459345c614b988c221c5392dae74056855c1f70667054f7459","source":{"kind":"arxiv","id":"2312.10628","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10628","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10628v2","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10628","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"7767ZROVOL4E","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"7767ZROVOL4ELE2F","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"7767ZROV","created_at":"2026-07-05T07:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7767ZROVOL4ELE2FYYKLTCGCEH","target":"record","payload":{"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"},"canonical_sha256":"fffdfcc5d572f8459345c614b988c221c5392dae74056855c1f70667054f7459","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"},"source_kind":"arxiv","source_id":"2312.10628","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tDqUIvTa4ZPj0vDczKE8ryMD55CanaSX7QLQB1mieVwbRFG0Ioxwco9Xy0pj18vB16m/OffF2Z1ZB3ZaLXKzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:33:03.069603Z"},"content_sha256":"30750df8e5cdf98b3a07509037951e9a941dd5c09f1b4f8088c95f2d6f55360d","schema_version":"1.0","event_id":"sha256:30750df8e5cdf98b3a07509037951e9a941dd5c09f1b4f8088c95f2d6f55360d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7767ZROVOL4ELE2FYYKLTCGCEH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePovZBJ9mkrmB0iJ3q0ntoIkVS6zO6vOSVfDl68uW5c+RhWshR7vHX7WFna52Up9dBgrMALdKX7+PhhAyhx8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:33:03.070070Z"},"content_sha256":"38878aab938c559b9d1e85e0700efe341f6cf93e523575d1713b88a95fdbd188","schema_version":"1.0","event_id":"sha256:38878aab938c559b9d1e85e0700efe341f6cf93e523575d1713b88a95fdbd188"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/bundle.json","state_url":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7767ZROVOL4ELE2FYYKLTCGCEH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T15:33:03Z","links":{"resolver":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH","bundle":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/bundle.json","state":"https://pith.science/pith/7767ZROVOL4ELE2FYYKLTCGCEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7767ZROVOL4ELE2FYYKLTCGCEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7767ZROVOL4ELE2FYYKLTCGCEH","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":"1061f92f363ccc694ecfdb000c27c02d67473c7b4a8f41c03eb09a9e2ea17103","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T06:58:31Z","title_canon_sha256":"5840be791f93b2d4670b289e3a72797a4fb8b6112a3231d8160f9dd2c9507204"},"schema_version":"1.0","source":{"id":"2312.10628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10628","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10628v2","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10628","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"7767ZROVOL4E","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"7767ZROVOL4ELE2F","created_at":"2026-07-05T07:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"7767ZROV","created_at":"2026-07-05T07:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:38878aab938c559b9d1e85e0700efe341f6cf93e523575d1713b88a95fdbd188","target":"graph","created_at":"2026-07-05T07:27:54Z","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/2312.10628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Congyi Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T06:58:31Z","title":"T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10628","kind":"arxiv","version":2},"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":"sha256:30750df8e5cdf98b3a07509037951e9a941dd5c09f1b4f8088c95f2d6f55360d","target":"record","created_at":"2026-07-05T07:27:54Z","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":"1061f92f363ccc694ecfdb000c27c02d67473c7b4a8f41c03eb09a9e2ea17103","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T06:58:31Z","title_canon_sha256":"5840be791f93b2d4670b289e3a72797a4fb8b6112a3231d8160f9dd2c9507204"},"schema_version":"1.0","source":{"id":"2312.10628","kind":"arxiv","version":2}},"canonical_sha256":"fffdfcc5d572f8459345c614b988c221c5392dae74056855c1f70667054f7459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fffdfcc5d572f8459345c614b988c221c5392dae74056855c1f70667054f7459","first_computed_at":"2026-07-05T07:27:54.272414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:54.272414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I53lXwCGeH3FmqXoRhG6jP/EvdydOGqUo4qUjBnxaO45RR08EpU1kgtJYPiWT3jXgwTF6IUUuOOVIl+59mInCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:54.273044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30750df8e5cdf98b3a07509037951e9a941dd5c09f1b4f8088c95f2d6f55360d","sha256:38878aab938c559b9d1e85e0700efe341f6cf93e523575d1713b88a95fdbd188"],"state_sha256":"c46b1980416082bbe2d4107788362bfe25618021a7827b8b3db8e04d44749e5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Udv7Z7L6azpsoUah2/dzgLqSm0KQphpYKh+zb8iZLZ5xs+zoaVqhV3sg6W+KgRR1s9elziE0miS/m4KTWinCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:33:03.074269Z","bundle_sha256":"760cea18275e81e686c4b0cc0ce9f5a59feefc9e1999de9a3d44930dec3d37d6"}}