{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MC7BCTOCYXP75UB3QOWPDJ3HBK","short_pith_number":"pith:MC7BCTOC","schema_version":"1.0","canonical_sha256":"60be114dc2c5dffed03b83acf1a7670ab4b3f8f536c05005d8188fc41a083a45","source":{"kind":"arxiv","id":"2210.12315","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Le Kang, Xin Zhou, Zhihong Pan, Zhiyuan Ren","submitted_at":"2022-10-22T00:41:17Z","abstract_excerpt":"We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use classical generative architecture, we apply the Denoising Diffusion Probabilistic Model to this task, synthesizing diverse motion results under the guidance of texts. The diffusion model converts white noise into structured 3D motion by a Markov process with a series of denoising steps and is efficiently trained by optimizing a variational lower bound. To achiev"},"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":"2210.12315","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-22T00:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"33cdc106d512b63d64031eaaa3df2669fee7e606fa2f52a9b3489ec0ae16e48f","abstract_canon_sha256":"30b1c094ed6b4073de586fccbc1ef7391d89ac7e16bc1811b25898d37b40fa87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:57.432534Z","signature_b64":"tznW0UxWK69p5uUYwR2xnvhTV+dV3DxIGAZwub7d9cBSzAiR4BcCA8BtORgZIstVPbp6A2RMPr1BNnN+97meAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60be114dc2c5dffed03b83acf1a7670ab4b3f8f536c05005d8188fc41a083a45","last_reissued_at":"2026-07-05T06:00:57.432065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:57.432065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Le Kang, Xin Zhou, Zhihong Pan, Zhiyuan Ren","submitted_at":"2022-10-22T00:41:17Z","abstract_excerpt":"We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use classical generative architecture, we apply the Denoising Diffusion Probabilistic Model to this task, synthesizing diverse motion results under the guidance of texts. The diffusion model converts white noise into structured 3D motion by a Markov process with a series of denoising steps and is efficiently trained by optimizing a variational lower bound. To achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12315","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/2210.12315/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":"2210.12315","created_at":"2026-07-05T06:00:57.432123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12315v2","created_at":"2026-07-05T06:00:57.432123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12315","created_at":"2026-07-05T06:00:57.432123+00:00"},{"alias_kind":"pith_short_12","alias_value":"MC7BCTOCYXP7","created_at":"2026-07-05T06:00:57.432123+00:00"},{"alias_kind":"pith_short_16","alias_value":"MC7BCTOCYXP75UB3","created_at":"2026-07-05T06:00:57.432123+00:00"},{"alias_kind":"pith_short_8","alias_value":"MC7BCTOC","created_at":"2026-07-05T06:00:57.432123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03191","citing_title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","ref_index":131,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK","json":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK.json","graph_json":"https://pith.science/api/pith-number/MC7BCTOCYXP75UB3QOWPDJ3HBK/graph.json","events_json":"https://pith.science/api/pith-number/MC7BCTOCYXP75UB3QOWPDJ3HBK/events.json","paper":"https://pith.science/paper/MC7BCTOC"},"agent_actions":{"view_html":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK","download_json":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK.json","view_paper":"https://pith.science/paper/MC7BCTOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12315&json=true","fetch_graph":"https://pith.science/api/pith-number/MC7BCTOCYXP75UB3QOWPDJ3HBK/graph.json","fetch_events":"https://pith.science/api/pith-number/MC7BCTOCYXP75UB3QOWPDJ3HBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK/action/storage_attestation","attest_author":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK/action/author_attestation","sign_citation":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK/action/citation_signature","submit_replication":"https://pith.science/pith/MC7BCTOCYXP75UB3QOWPDJ3HBK/action/replication_record"}},"created_at":"2026-07-05T06:00:57.432123+00:00","updated_at":"2026-07-05T06:00:57.432123+00:00"}