{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NYFEGIJWUS3VTYEL7FY73SYBZV","short_pith_number":"pith:NYFEGIJW","schema_version":"1.0","canonical_sha256":"6e0a432136a4b759e08bf971fdcb01cd7f60d02dbcc621a6406dcb04119085bc","source":{"kind":"arxiv","id":"2605.12778","version":1},"attestation_state":"computed","paper":{"title":"Generative Motion In-betweening by Diffusion over Continuous Implicit Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Latent diffusion on implicit neural representations generates plausible motions from sparse keyframes.","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Edmond S. L. Ho, Paul Henderson, Shiyu Fan","submitted_at":"2026-05-12T21:48:14Z","abstract_excerpt":"Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for more complex, varied, and realistic motion transitions. However, recent methods still exhibit noticeable limitations in preserving keyframe information and ensuring motion continuity. In this paper, we propose a novel pipeline and sampling optimization strategy for latent diffusion models (LDM) based on motion implicit neural representations (INR). By establishing a mapping between INR and sparse spatial or temporal information within latent diffusion, our model can sample the INR parame"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.12778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-12T21:48:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"90ee90f423f73b187d26134fa4b7378637779f5c252031603a843df44ebf662a","abstract_canon_sha256":"013b8abd45c03ca4b521e045b576c84fa9d0c1cec995a94c334de3a9e65a704b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:13.185178Z","signature_b64":"VwPygZPJqxFeRVImKBDUXl3VUltkb9L5YC8J+WmlSr8/9Q6RAeD9NXZb8oBlTnKbrtBp0IE/uyPUEU5ZbDpkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e0a432136a4b759e08bf971fdcb01cd7f60d02dbcc621a6406dcb04119085bc","last_reissued_at":"2026-05-18T03:09:13.184693Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:13.184693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Motion In-betweening by Diffusion over Continuous Implicit Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Latent diffusion on implicit neural representations generates plausible motions from sparse keyframes.","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Edmond S. L. Ho, Paul Henderson, Shiyu Fan","submitted_at":"2026-05-12T21:48:14Z","abstract_excerpt":"Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for more complex, varied, and realistic motion transitions. However, recent methods still exhibit noticeable limitations in preserving keyframe information and ensuring motion continuity. In this paper, we propose a novel pipeline and sampling optimization strategy for latent diffusion models (LDM) based on motion implicit neural representations (INR). By establishing a mapping between INR and sparse spatial or temporal information within latent diffusion, our model can sample the INR parame"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By establishing a mapping between INR and sparse spatial or temporal information within latent diffusion, our model can sample the INR parameters from extremely sparse and ambiguous keyframe data and reconstruct plausible and smooth motions from the manifold.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a learned mapping from sparse keyframes into the latent space of an INR-based diffusion model will reliably produce motions that remain both accurate at the keyframes and continuous in between without additional post-processing or constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A latent diffusion model over continuous implicit neural representations samples INR parameters from sparse keyframes to reconstruct plausible, smooth, and diverse motions while preserving keyframe accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Latent diffusion on implicit neural representations generates plausible motions from sparse keyframes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"632f158954666f4bdb67b4ff732ccdb6ee19e034b5bad4799169b2a13ca58d7b"},"source":{"id":"2605.12778","kind":"arxiv","version":1},"verdict":{"id":"b59c2865-3ea8-4992-af74-35390483b538","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:26:44.815042Z","strongest_claim":"By establishing a mapping between INR and sparse spatial or temporal information within latent diffusion, our model can sample the INR parameters from extremely sparse and ambiguous keyframe data and reconstruct plausible and smooth motions from the manifold.","one_line_summary":"A latent diffusion model over continuous implicit neural representations samples INR parameters from sparse keyframes to reconstruct plausible, smooth, and diverse motions while preserving keyframe accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a learned mapping from sparse keyframes into the latent space of an INR-based diffusion model will reliably produce motions that remain both accurate at the keyframes and continuous in between without additional post-processing or constraints.","pith_extraction_headline":"Latent diffusion on implicit neural representations generates plausible motions from sparse keyframes."},"references":{"count":49,"sample":[{"doi":"","year":2020,"title":"F. G. Harvey, M. Yurick, D. Nowrouzezahrai, and C. Pal, “Robust motion in-betweening,”ACM Trans. Graph., vol. 39, no. 4, 2020","work_id":"495e73af-2ada-49e4-ade5-f7d835a7977e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Denoising diffusion probabilistic models","work_id":"556bc6b5-6607-4a7d-871d-59b4cb93e3c9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Human motion diffusion model,","work_id":"79b5ac63-345c-492d-a746-7f60035cff43","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Motiondiffuse: Text-driven human motion generation with diffusion model,","work_id":"25626e8b-9af8-4a6f-9741-0070c198b234","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Omnicontrol: Control any joint at any time for human motion generation,","work_id":"8a3c7dcc-6b33-4460-aac0-9b8368bf0ec6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":49,"snapshot_sha256":"b059ca3f5ab9cc8760f85d4e3429aec886ec60dc1c306ee02833b5ee4ccdde6f","internal_anchors":1},"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":"2605.12778","created_at":"2026-05-18T03:09:13.184764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12778v1","created_at":"2026-05-18T03:09:13.184764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12778","created_at":"2026-05-18T03:09:13.184764+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYFEGIJWUS3V","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYFEGIJWUS3VTYEL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYFEGIJW","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV","json":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV.json","graph_json":"https://pith.science/api/pith-number/NYFEGIJWUS3VTYEL7FY73SYBZV/graph.json","events_json":"https://pith.science/api/pith-number/NYFEGIJWUS3VTYEL7FY73SYBZV/events.json","paper":"https://pith.science/paper/NYFEGIJW"},"agent_actions":{"view_html":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV","download_json":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV.json","view_paper":"https://pith.science/paper/NYFEGIJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12778&json=true","fetch_graph":"https://pith.science/api/pith-number/NYFEGIJWUS3VTYEL7FY73SYBZV/graph.json","fetch_events":"https://pith.science/api/pith-number/NYFEGIJWUS3VTYEL7FY73SYBZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV/action/storage_attestation","attest_author":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV/action/author_attestation","sign_citation":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV/action/citation_signature","submit_replication":"https://pith.science/pith/NYFEGIJWUS3VTYEL7FY73SYBZV/action/replication_record"}},"created_at":"2026-05-18T03:09:13.184764+00:00","updated_at":"2026-05-18T03:09:13.184764+00:00"}