{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TYYJGRV3ODYWISNOVRTBRXI4IH","short_pith_number":"pith:TYYJGRV3","schema_version":"1.0","canonical_sha256":"9e309346bb70f16449aeac6618dd1c41fb53bb1e2cb4635a355b60814b5ddb7a","source":{"kind":"arxiv","id":"2411.16575","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaizu Jiang, Xiaogang Peng, Yiming Xie, Zeyu Han, Zichong Meng","submitted_at":"2024-11-25T16:59:42Z","abstract_excerpt":"Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them "},"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":"2411.16575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T16:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"89064cee88f5c85696c4c953003ebfae81bec20e198dd9b494a449369b1823f7","abstract_canon_sha256":"c638d432bdef8f0fc31a8296a9c5ec220f33a5491b310e79f690b4a29f4018c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:02.372016Z","signature_b64":"Ywn/YCUGzA0z/rktZdXj067+N0Ymws4x2YgxDoWCySKJVL7Oum78ks+lRv7pz37C/GH39kj1Sz/33ctgIfWlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e309346bb70f16449aeac6618dd1c41fb53bb1e2cb4635a355b60814b5ddb7a","last_reissued_at":"2026-07-05T11:34:02.371552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:02.371552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaizu Jiang, Xiaogang Peng, Yiming Xie, Zeyu Han, Zichong Meng","submitted_at":"2024-11-25T16:59:42Z","abstract_excerpt":"Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16575","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/2411.16575/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":"2411.16575","created_at":"2026-07-05T11:34:02.371607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16575v2","created_at":"2026-07-05T11:34:02.371607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16575","created_at":"2026-07-05T11:34:02.371607+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYYJGRV3ODYW","created_at":"2026-07-05T11:34:02.371607+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYYJGRV3ODYWISNO","created_at":"2026-07-05T11:34:02.371607+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYYJGRV3","created_at":"2026-07-05T11:34:02.371607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.11334","citing_title":"MARRS: Masked Autoregressive Unit-based Reaction Synthesis","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07820","citing_title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03799","citing_title":"Next-Scale Autoregressive Models for Text-to-Motion Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11704","citing_title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH","json":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH.json","graph_json":"https://pith.science/api/pith-number/TYYJGRV3ODYWISNOVRTBRXI4IH/graph.json","events_json":"https://pith.science/api/pith-number/TYYJGRV3ODYWISNOVRTBRXI4IH/events.json","paper":"https://pith.science/paper/TYYJGRV3"},"agent_actions":{"view_html":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH","download_json":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH.json","view_paper":"https://pith.science/paper/TYYJGRV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16575&json=true","fetch_graph":"https://pith.science/api/pith-number/TYYJGRV3ODYWISNOVRTBRXI4IH/graph.json","fetch_events":"https://pith.science/api/pith-number/TYYJGRV3ODYWISNOVRTBRXI4IH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH/action/storage_attestation","attest_author":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH/action/author_attestation","sign_citation":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH/action/citation_signature","submit_replication":"https://pith.science/pith/TYYJGRV3ODYWISNOVRTBRXI4IH/action/replication_record"}},"created_at":"2026-07-05T11:34:02.371607+00:00","updated_at":"2026-07-05T11:34:02.371607+00:00"}