{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3J6HNJT4VTSV3UADQAIH4FXTWT","short_pith_number":"pith:3J6HNJT4","schema_version":"1.0","canonical_sha256":"da7c76a67cace55dd00380107e16f3b4e25c3d8ae3e9b576e132529c941500e4","source":{"kind":"arxiv","id":"2408.00370","version":1},"attestation_state":"computed","paper":{"title":"DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SD"],"primary_cat":"cs.GR","authors_text":"Bozuo Zhao, Fan Zhang, Fuxing Gao, Hui Du, Jiayang Zhu, Jingmei Wu, Leyao Yan, Naye Ji, WeiFan Zhong, Xiaomeng Ma, Yanbing Jiang, Zhenqing Ye","submitted_at":"2024-08-01T08:22:47Z","abstract_excerpt":"Speech-driven gesture generation is an emerging domain within virtual human creation, where current methods predominantly utilize Transformer-based architectures that necessitate extensive memory and are characterized by slow inference speeds. In response to these limitations, we propose \\textit{DiM-Gestures}, a novel end-to-end generative model crafted to create highly personalized 3D full-body gestures solely from raw speech audio, employing Mamba-based architectures. This model integrates a Mamba-based fuzzy feature extractor with a non-autoregressive Adaptive Layer Normalization (AdaLN) Ma"},"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":"2408.00370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2024-08-01T08:22:47Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SD"],"title_canon_sha256":"3df1207f10b5ed2f5e2fa5ee89562eb0b2e86d6a80657201835316a4156100f1","abstract_canon_sha256":"4b1eef5eafd0d73260ce61c1212a3963331cfa6ac8abdae833315c4e916a4a21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:02.690482Z","signature_b64":"WrhFdOHoIUVjVfX8WN082hz3nt+cRhq4w3m226VHanxrxcqducAFa3BfFPveaPgYIlwZswz5FGW0T3fz8LocAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da7c76a67cace55dd00380107e16f3b4e25c3d8ae3e9b576e132529c941500e4","last_reissued_at":"2026-07-05T08:51:02.689988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:02.689988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SD"],"primary_cat":"cs.GR","authors_text":"Bozuo Zhao, Fan Zhang, Fuxing Gao, Hui Du, Jiayang Zhu, Jingmei Wu, Leyao Yan, Naye Ji, WeiFan Zhong, Xiaomeng Ma, Yanbing Jiang, Zhenqing Ye","submitted_at":"2024-08-01T08:22:47Z","abstract_excerpt":"Speech-driven gesture generation is an emerging domain within virtual human creation, where current methods predominantly utilize Transformer-based architectures that necessitate extensive memory and are characterized by slow inference speeds. In response to these limitations, we propose \\textit{DiM-Gestures}, a novel end-to-end generative model crafted to create highly personalized 3D full-body gestures solely from raw speech audio, employing Mamba-based architectures. This model integrates a Mamba-based fuzzy feature extractor with a non-autoregressive Adaptive Layer Normalization (AdaLN) Ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00370","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/2408.00370/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":"2408.00370","created_at":"2026-07-05T08:51:02.690048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00370v1","created_at":"2026-07-05T08:51:02.690048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00370","created_at":"2026-07-05T08:51:02.690048+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J6HNJT4VTSV","created_at":"2026-07-05T08:51:02.690048+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J6HNJT4VTSV3UAD","created_at":"2026-07-05T08:51:02.690048+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J6HNJT4","created_at":"2026-07-05T08:51:02.690048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17923","citing_title":"AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT","json":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT.json","graph_json":"https://pith.science/api/pith-number/3J6HNJT4VTSV3UADQAIH4FXTWT/graph.json","events_json":"https://pith.science/api/pith-number/3J6HNJT4VTSV3UADQAIH4FXTWT/events.json","paper":"https://pith.science/paper/3J6HNJT4"},"agent_actions":{"view_html":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT","download_json":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT.json","view_paper":"https://pith.science/paper/3J6HNJT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00370&json=true","fetch_graph":"https://pith.science/api/pith-number/3J6HNJT4VTSV3UADQAIH4FXTWT/graph.json","fetch_events":"https://pith.science/api/pith-number/3J6HNJT4VTSV3UADQAIH4FXTWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT/action/storage_attestation","attest_author":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT/action/author_attestation","sign_citation":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT/action/citation_signature","submit_replication":"https://pith.science/pith/3J6HNJT4VTSV3UADQAIH4FXTWT/action/replication_record"}},"created_at":"2026-07-05T08:51:02.690048+00:00","updated_at":"2026-07-05T08:51:02.690048+00:00"}