{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6RR77ZAEQNDTA6NHRWFXDKZQLO","short_pith_number":"pith:6RR77ZAE","canonical_record":{"source":{"id":"2209.14916","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T16:27:53Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"35607a551d789646ae0f20afbde072ed395b8824a618a0b36b1e2614f96b35d7","abstract_canon_sha256":"c0b9c2d8fc337f851c239bf0ba9d09df604c3ab48c8c6b4fd7eb3b3770ba84a9"},"schema_version":"1.0"},"canonical_sha256":"f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e","source":{"kind":"arxiv","id":"2209.14916","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14916","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14916v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14916","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"6RR77ZAEQNDT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"6RR77ZAEQNDTA6NH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"6RR77ZAE","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6RR77ZAEQNDTA6NHRWFXDKZQLO","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14916","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T16:27:53Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"35607a551d789646ae0f20afbde072ed395b8824a618a0b36b1e2614f96b35d7","abstract_canon_sha256":"c0b9c2d8fc337f851c239bf0ba9d09df604c3ab48c8c6b4fd7eb3b3770ba84a9"},"schema_version":"1.0"},"canonical_sha256":"f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.689955Z","signature_b64":"7VsHpyJMWdwmYYFB3TtwJh+m5e0aLP/xxpwnezyARmPPCzgmCs6r32Vk4+fEq1dRFU2d1wxMTQzwroPoxfLxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e","last_reissued_at":"2026-05-17T23:38:53.689359Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.689359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14916","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":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YrCy1asK9TlvYnMaFGfSXus5wRkKUxsHvvM+q3l35rC0N2YTrt1s8yCIc/Dk3750SwdZJP2TEU/JT4t/AS9hAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:44:38.962464Z"},"content_sha256":"ee6df5a54437136970133ecb3ae938281a314a30917a5ca573f2bf9222a73ecc","schema_version":"1.0","event_id":"sha256:ee6df5a54437136970133ecb3ae938281a314a30917a5ca573f2bf9222a73ecc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6RR77ZAEQNDTA6NHRWFXDKZQLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human Motion Diffusion Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Amit H. Bermano, Brian Gordon, Daniel Cohen-Or, Guy Tevet, Sigal Raab, Yonatan Shafir","submitted_at":"2022-09-29T16:27:53Z","abstract_excerpt":"Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it. Therefore, current generative solutions are either low-quality or limited in expressiveness. Diffusion models, which have already shown remarkable generative capabilities in other domains, are promising candidates for human motion due to their many-to-many nature, but they tend to be resource hungry and hard to control. In this paper, we introduce Motion Diff"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That predicting the clean sample (instead of noise) at each diffusion step, combined with geometric losses, will reliably produce higher-quality and more controllable motions than standard noise-prediction diffusion on the chosen motion datasets and benchmarks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0567be8895ce36e12786533e9d083fe0ccf9df00b682d50a4f6dd0455ceca461"},"source":{"id":"2209.14916","kind":"arxiv","version":2},"verdict":{"id":"d79af2a1-7e01-480e-aade-2c3bf331d15f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:18:23.208904Z","strongest_claim":"MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion.","one_line_summary":"MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That predicting the clean sample (instead of noise) at each diffusion step, combined with geometric losses, will reliably produce higher-quality and more controllable motions than standard noise-prediction diffusion on the chosen motion datasets and benchmarks.","pith_extraction_headline":"A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise."},"references":{"count":20,"sample":[{"doi":"","year":2021,"title":"Accessed: 2021-12-25","work_id":"d78252bc-a5af-4850-872f-ce390aa95f1d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"A spatio-temporal transformer for 3d human motion prediction","work_id":"7c6af718-79c5-4bbb-bf00-d42954a24f4f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Text2gestures: A transformer-based network for generating emotive body ges- tures for virtual agents","work_id":"fd721ccb-ee42-4e1d-815f-0ca9cbc7501c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Implicit neural representations for variable length human motion generation","work_id":"b08e0813-fe00-4320-ad67-024ad0273606","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","work_id":"af085a26-bb72-4b1a-8e38-107776555081","ref_index":5,"cited_arxiv_id":"1406.1078","is_internal_anchor":true}],"resolved_work":20,"snapshot_sha256":"cf93bbf24451a844a0c6eeca83d2f83f4be8491b3e3a9aa16e5bbad6f2aaad2e","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3bdcdb8100ff192648662a8a312853cac0a789b0b2da1b3bfde1f58f9be03eb9"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d79af2a1-7e01-480e-aade-2c3bf331d15f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2SA87WXIuLxABgiYu+DWflbWj1sKVlLVPKR2n6ybH49Y9TPM57vxDdsNjBcv302hzByNAbmntzFvtFdoSJOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:44:38.963021Z"},"content_sha256":"c11b88f791342552adfa8c8b96edfd63474599c16eae0aba3d2696d22cc1ef0c","schema_version":"1.0","event_id":"sha256:c11b88f791342552adfa8c8b96edfd63474599c16eae0aba3d2696d22cc1ef0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO/bundle.json","state_url":"https://pith.science/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO/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":"2026-05-30T02:44:38Z","links":{"resolver":"https://pith.science/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO","bundle":"https://pith.science/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO/bundle.json","state":"https://pith.science/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6RR77ZAEQNDTA6NHRWFXDKZQLO","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":"c0b9c2d8fc337f851c239bf0ba9d09df604c3ab48c8c6b4fd7eb3b3770ba84a9","cross_cats_sorted":["cs.GR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T16:27:53Z","title_canon_sha256":"35607a551d789646ae0f20afbde072ed395b8824a618a0b36b1e2614f96b35d7"},"schema_version":"1.0","source":{"id":"2209.14916","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14916","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14916v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14916","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"6RR77ZAEQNDT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"6RR77ZAEQNDTA6NH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"6RR77ZAE","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:c11b88f791342552adfa8c8b96edfd63474599c16eae0aba3d2696d22cc1ef0c","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That predicting the clean sample (instead of noise) at each diffusion step, combined with geometric losses, will reliably produce higher-quality and more controllable motions than standard noise-prediction diffusion on the chosen motion datasets and benchmarks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise."}],"snapshot_sha256":"0567be8895ce36e12786533e9d083fe0ccf9df00b682d50a4f6dd0455ceca461"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3bdcdb8100ff192648662a8a312853cac0a789b0b2da1b3bfde1f58f9be03eb9"},"paper":{"abstract_excerpt":"Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it. Therefore, current generative solutions are either low-quality or limited in expressiveness. Diffusion models, which have already shown remarkable generative capabilities in other domains, are promising candidates for human motion due to their many-to-many nature, but they tend to be resource hungry and hard to control. In this paper, we introduce Motion Diff","authors_text":"Amit H. Bermano, Brian Gordon, Daniel Cohen-Or, Guy Tevet, Sigal Raab, Yonatan Shafir","cross_cats":["cs.GR"],"headline":"A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T16:27:53Z","title":"Human Motion Diffusion Model"},"references":{"count":20,"internal_anchors":9,"resolved_work":20,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Accessed: 2021-12-25","work_id":"d78252bc-a5af-4850-872f-ce390aa95f1d","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A spatio-temporal transformer for 3d human motion prediction","work_id":"7c6af718-79c5-4bbb-bf00-d42954a24f4f","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Text2gestures: A transformer-based network for generating emotive body ges- tures for virtual agents","work_id":"fd721ccb-ee42-4e1d-815f-0ca9cbc7501c","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Implicit neural representations for variable length human motion generation","work_id":"b08e0813-fe00-4320-ad67-024ad0273606","year":null},{"cited_arxiv_id":"1406.1078","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","work_id":"af085a26-bb72-4b1a-8e38-107776555081","year":null}],"snapshot_sha256":"cf93bbf24451a844a0c6eeca83d2f83f4be8491b3e3a9aa16e5bbad6f2aaad2e"},"source":{"id":"2209.14916","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T03:18:23.208904Z","id":"d79af2a1-7e01-480e-aade-2c3bf331d15f","model_set":{"reader":"grok-4.3"},"one_line_summary":"MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise.","strongest_claim":"MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion.","weakest_assumption":"That predicting the clean sample (instead of noise) at each diffusion step, combined with geometric losses, will reliably produce higher-quality and more controllable motions than standard noise-prediction diffusion on the chosen motion datasets and benchmarks."}},"verdict_id":"d79af2a1-7e01-480e-aade-2c3bf331d15f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ee6df5a54437136970133ecb3ae938281a314a30917a5ca573f2bf9222a73ecc","target":"record","created_at":"2026-05-17T23:38:53Z","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":"c0b9c2d8fc337f851c239bf0ba9d09df604c3ab48c8c6b4fd7eb3b3770ba84a9","cross_cats_sorted":["cs.GR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T16:27:53Z","title_canon_sha256":"35607a551d789646ae0f20afbde072ed395b8824a618a0b36b1e2614f96b35d7"},"schema_version":"1.0","source":{"id":"2209.14916","kind":"arxiv","version":2}},"canonical_sha256":"f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e","first_computed_at":"2026-05-17T23:38:53.689359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.689359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7VsHpyJMWdwmYYFB3TtwJh+m5e0aLP/xxpwnezyARmPPCzgmCs6r32Vk4+fEq1dRFU2d1wxMTQzwroPoxfLxAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.689955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14916","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee6df5a54437136970133ecb3ae938281a314a30917a5ca573f2bf9222a73ecc","sha256:c11b88f791342552adfa8c8b96edfd63474599c16eae0aba3d2696d22cc1ef0c"],"state_sha256":"23dfb4d25e931ac47096a03da26834eaf880f0d1a41f2e403744ca3cd6286b95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"962o5JV6p0SxTPPVnzpQjInTUjVp/bX8UodtNpQvieSPQoeOoz3DxMam4lYG/F9yN8/FCOBzLM/EeojjOmRGBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:44:38.965736Z","bundle_sha256":"9c3662b9906594519da5133062186359f017f3dbb69514980e38eca52eca061b"}}