{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DO4CINESDUB3HKN2SP6J6R7TCQ","short_pith_number":"pith:DO4CINES","schema_version":"1.0","canonical_sha256":"1bb82434921d03b3a9ba93fc9f47f314258afafc28f6065dab06211ef00ef707","source":{"kind":"arxiv","id":"2304.01116","version":1},"attestation_state":"computed","paper":{"title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Huirong Li, Lei Yang, Liang Pan, Mingyuan Zhang, Xinying Guo, Zhongang Cai, Ziwei Liu","submitted_at":"2023-04-03T16:29:00Z","abstract_excerpt":"3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions. However, the performance on more diverse motions remains unsatisfactory. In this work, we propose ReMoDiffuse, a diffusion-model-based motion generation framework that integrates a retrieval mechanism to refine the denoising process. ReMoDiffuse enhances the generalizability and diversity of text-driven motion generation with three key designs: 1) Hybrid Retrieval finds approp"},"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":"2304.01116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T16:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"a2994a0e8dece5dabeb8c2c75f2d1c6406e9dca2236b360045ef5de63ae9a22c","abstract_canon_sha256":"09cddd76953042903c672f2bc829955943dcc7ec4bb6f7aaf045a54104ebb7ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:26.720924Z","signature_b64":"QlFx6+NitiJFq2vu7H3oqzHmFQ4RrlV/QMmJEQzcmZbORFnN8Lpz9dqfBmLYVsOBr30sDmj9MXD/y6jtBYHTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bb82434921d03b3a9ba93fc9f47f314258afafc28f6065dab06211ef00ef707","last_reissued_at":"2026-07-05T05:57:26.720336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:26.720336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Huirong Li, Lei Yang, Liang Pan, Mingyuan Zhang, Xinying Guo, Zhongang Cai, Ziwei Liu","submitted_at":"2023-04-03T16:29:00Z","abstract_excerpt":"3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions. However, the performance on more diverse motions remains unsatisfactory. In this work, we propose ReMoDiffuse, a diffusion-model-based motion generation framework that integrates a retrieval mechanism to refine the denoising process. ReMoDiffuse enhances the generalizability and diversity of text-driven motion generation with three key designs: 1) Hybrid Retrieval finds approp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01116","kind":"arxiv","version":1},"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/2304.01116/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":"2304.01116","created_at":"2026-07-05T05:57:26.720410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01116v1","created_at":"2026-07-05T05:57:26.720410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01116","created_at":"2026-07-05T05:57:26.720410+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO4CINESDUB3","created_at":"2026-07-05T05:57:26.720410+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO4CINESDUB3HKN2","created_at":"2026-07-05T05:57:26.720410+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO4CINES","created_at":"2026-07-05T05:57:26.720410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22726","citing_title":"Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11704","citing_title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ","json":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ.json","graph_json":"https://pith.science/api/pith-number/DO4CINESDUB3HKN2SP6J6R7TCQ/graph.json","events_json":"https://pith.science/api/pith-number/DO4CINESDUB3HKN2SP6J6R7TCQ/events.json","paper":"https://pith.science/paper/DO4CINES"},"agent_actions":{"view_html":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ","download_json":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ.json","view_paper":"https://pith.science/paper/DO4CINES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01116&json=true","fetch_graph":"https://pith.science/api/pith-number/DO4CINESDUB3HKN2SP6J6R7TCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DO4CINESDUB3HKN2SP6J6R7TCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ/action/storage_attestation","attest_author":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ/action/author_attestation","sign_citation":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ/action/citation_signature","submit_replication":"https://pith.science/pith/DO4CINESDUB3HKN2SP6J6R7TCQ/action/replication_record"}},"created_at":"2026-07-05T05:57:26.720410+00:00","updated_at":"2026-07-05T05:57:26.720410+00:00"}