{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7H34XRGIXCOITM3Q7WCCNAWM33","short_pith_number":"pith:7H34XRGI","schema_version":"1.0","canonical_sha256":"f9f7cbc4c8b89c89b370fd842682ccdeff1e00974367b8d56df1c8a06f6b1823","source":{"kind":"arxiv","id":"2303.01418","version":3},"attestation_state":"computed","paper":{"title":"Human Motion Diffusion as a Generative Prior","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Amit H. Bermano, Guy Tevet, Roy Kapon, Yonatan Shafir","submitted_at":"2023-03-02T17:09:27Z","abstract_excerpt":"Recent work has demonstrated the significant potential of denoising diffusion models for generating human motion, including text-to-motion capabilities. However, these methods are restricted by the paucity of annotated motion data, a focus on single-person motions, and a lack of detailed control. In this paper, we introduce three forms of composition based on diffusion priors: sequential, parallel, and model composition. Using sequential composition, we tackle the challenge of long sequence generation. We introduce DoubleTake, an inference-time method with which we generate long animations con"},"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":"2303.01418","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T17:09:27Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"a7101e200db77f3feffcb7313f0ab505f6da8de683f7694cd4c03a261ab348d1","abstract_canon_sha256":"d138d270d9633a64efb5e2c55696ef72d59c1848b53ffcc5766bdd22b13662fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:00.840060Z","signature_b64":"BR3KaP4da9bFZEHkwg6wDMggYZd1LBjPxr7PTL7jlX+k/OdfUX2u9OgJW1SitMaxk7D1COm/NVvTn9wDmdcNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f7cbc4c8b89c89b370fd842682ccdeff1e00974367b8d56df1c8a06f6b1823","last_reissued_at":"2026-07-05T06:46:00.839592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:00.839592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Motion Diffusion as a Generative Prior","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Amit H. Bermano, Guy Tevet, Roy Kapon, Yonatan Shafir","submitted_at":"2023-03-02T17:09:27Z","abstract_excerpt":"Recent work has demonstrated the significant potential of denoising diffusion models for generating human motion, including text-to-motion capabilities. However, these methods are restricted by the paucity of annotated motion data, a focus on single-person motions, and a lack of detailed control. In this paper, we introduce three forms of composition based on diffusion priors: sequential, parallel, and model composition. Using sequential composition, we tackle the challenge of long sequence generation. We introduce DoubleTake, an inference-time method with which we generate long animations con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01418","kind":"arxiv","version":3},"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/2303.01418/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":"2303.01418","created_at":"2026-07-05T06:46:00.839645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01418v3","created_at":"2026-07-05T06:46:00.839645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01418","created_at":"2026-07-05T06:46:00.839645+00:00"},{"alias_kind":"pith_short_12","alias_value":"7H34XRGIXCOI","created_at":"2026-07-05T06:46:00.839645+00:00"},{"alias_kind":"pith_short_16","alias_value":"7H34XRGIXCOITM3Q","created_at":"2026-07-05T06:46:00.839645+00:00"},{"alias_kind":"pith_short_8","alias_value":"7H34XRGI","created_at":"2026-07-05T06:46:00.839645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07880","citing_title":"GIRAF: Towards Generalizable Human Interactions with Articulated Objects","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26981","citing_title":"In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18243","citing_title":"MOCHI: Motion Enhancement of Collaborative Human-object Interactions","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11334","citing_title":"MARRS: Masked Autoregressive Unit-based Reaction Synthesis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20955","citing_title":"DrawMotion: Generating 3D Human Motions by Freehand Drawing","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23468","citing_title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20187","citing_title":"MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02973","citing_title":"Exploring Motion-Language Alignment for Text-driven Motion Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24833","citing_title":"MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22164","citing_title":"Learning Reactive Human Motion Generation from Paired Interaction Data Using Transformer-Based Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00517","citing_title":"PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19105","citing_title":"EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08509","citing_title":"Visually-grounded Humanoid Agents","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20336","citing_title":"Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33","json":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33.json","graph_json":"https://pith.science/api/pith-number/7H34XRGIXCOITM3Q7WCCNAWM33/graph.json","events_json":"https://pith.science/api/pith-number/7H34XRGIXCOITM3Q7WCCNAWM33/events.json","paper":"https://pith.science/paper/7H34XRGI"},"agent_actions":{"view_html":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33","download_json":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33.json","view_paper":"https://pith.science/paper/7H34XRGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01418&json=true","fetch_graph":"https://pith.science/api/pith-number/7H34XRGIXCOITM3Q7WCCNAWM33/graph.json","fetch_events":"https://pith.science/api/pith-number/7H34XRGIXCOITM3Q7WCCNAWM33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33/action/storage_attestation","attest_author":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33/action/author_attestation","sign_citation":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33/action/citation_signature","submit_replication":"https://pith.science/pith/7H34XRGIXCOITM3Q7WCCNAWM33/action/replication_record"}},"created_at":"2026-07-05T06:46:00.839645+00:00","updated_at":"2026-07-05T06:46:00.839645+00:00"}