{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KZ4NMIY7QZ6GX37TGT6U526EWA","short_pith_number":"pith:KZ4NMIY7","schema_version":"1.0","canonical_sha256":"5678d6231f867c6beff334fd4eebc4b011e9e52f8ef94df20d2a8a8e12860d4f","source":{"kind":"arxiv","id":"2003.08802","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Maosen Li, Qi Tian, Siheng Chen, Yanfeng Wang, Yangheng Zhao, Ya Zhang","submitted_at":"2020-03-17T02:49:51Z","abstract_excerpt":"We propose novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning. This multiscale graph is adaptive during training and dynamic across network layers. Based on this graph, we propose a multiscale graph computational unit (MGCU) to extract features at individual scales and fuse features across scales. The entire model is action-category-agnostic and follows an encoder-decoder framework. The encoder consists o"},"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":"2003.08802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-17T02:49:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"28d3522edc768f7cc092098029f2a1ba72d894239844ab147b1389098ba481bc","abstract_canon_sha256":"e493ac62edaedba3e3ebe0f9cec99243c26011fb98b8b02853159be1f6e8e74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:14.301647Z","signature_b64":"I5FVjflz/1hpQPR56HF8CRc2GViqDZibNaqaUkmvj9jU4VCsZOUPZJa8sOyjWVRUelSTtZ1mYi68bce1e/8RBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5678d6231f867c6beff334fd4eebc4b011e9e52f8ef94df20d2a8a8e12860d4f","last_reissued_at":"2026-07-05T00:49:14.301221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:14.301221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Maosen Li, Qi Tian, Siheng Chen, Yanfeng Wang, Yangheng Zhao, Ya Zhang","submitted_at":"2020-03-17T02:49:51Z","abstract_excerpt":"We propose novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning. This multiscale graph is adaptive during training and dynamic across network layers. Based on this graph, we propose a multiscale graph computational unit (MGCU) to extract features at individual scales and fuse features across scales. The entire model is action-category-agnostic and follows an encoder-decoder framework. The encoder consists o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08802","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/2003.08802/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":"2003.08802","created_at":"2026-07-05T00:49:14.301271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.08802v1","created_at":"2026-07-05T00:49:14.301271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08802","created_at":"2026-07-05T00:49:14.301271+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ4NMIY7QZ6G","created_at":"2026-07-05T00:49:14.301271+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ4NMIY7QZ6GX37T","created_at":"2026-07-05T00:49:14.301271+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ4NMIY7","created_at":"2026-07-05T00:49:14.301271+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/KZ4NMIY7QZ6GX37TGT6U526EWA","json":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA.json","graph_json":"https://pith.science/api/pith-number/KZ4NMIY7QZ6GX37TGT6U526EWA/graph.json","events_json":"https://pith.science/api/pith-number/KZ4NMIY7QZ6GX37TGT6U526EWA/events.json","paper":"https://pith.science/paper/KZ4NMIY7"},"agent_actions":{"view_html":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA","download_json":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA.json","view_paper":"https://pith.science/paper/KZ4NMIY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.08802&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ4NMIY7QZ6GX37TGT6U526EWA/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ4NMIY7QZ6GX37TGT6U526EWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA/action/storage_attestation","attest_author":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA/action/author_attestation","sign_citation":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA/action/citation_signature","submit_replication":"https://pith.science/pith/KZ4NMIY7QZ6GX37TGT6U526EWA/action/replication_record"}},"created_at":"2026-07-05T00:49:14.301271+00:00","updated_at":"2026-07-05T00:49:14.301271+00:00"}