{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TCM4TXRD3Q63BRVRPCO6X6PEMR","short_pith_number":"pith:TCM4TXRD","schema_version":"1.0","canonical_sha256":"9899c9de23dc3db0c6b1789debf9e4646be0dffac0757e97f8bc7ddb5358a939","source":{"kind":"arxiv","id":"2304.04956","version":1},"attestation_state":"computed","paper":{"title":"Multi-Graph Convolution Network for Pose Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongwei Ren, Kewei Liang, Yuhong Shi","submitted_at":"2023-04-11T03:59:43Z","abstract_excerpt":"Recently, there has been a growing interest in predicting human motion, which involves forecasting future body poses based on observed pose sequences. This task is complex due to modeling spatial and temporal relationships. The most commonly used models for this task are autoregressive models, such as recurrent neural networks (RNNs) or variants, and Transformer Networks. However, RNNs have several drawbacks, such as vanishing or exploding gradients. Other researchers have attempted to solve the communication problem in the spatial dimension by integrating Graph Convolutional Networks (GCN) an"},"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":"2304.04956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-11T03:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"5b16d9cd57064f5f747ebaeb4638bcbd18e07a350a1918e515190fc818b92173","abstract_canon_sha256":"8ead626043ce7a4203c95113143c5fa171014aa0410d511b7937ac5419458c1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:53.518579Z","signature_b64":"Zp360IJCld/xEYzwPI3iyjaL6hsrfQt+zl3cgcc9JbtlX+mRJm52WZoM1Q0LLY4QVBYIVBIjjNMD8SVYOJ0GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9899c9de23dc3db0c6b1789debf9e4646be0dffac0757e97f8bc7ddb5358a939","last_reissued_at":"2026-07-05T05:59:53.518093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:53.518093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Graph Convolution Network for Pose Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongwei Ren, Kewei Liang, Yuhong Shi","submitted_at":"2023-04-11T03:59:43Z","abstract_excerpt":"Recently, there has been a growing interest in predicting human motion, which involves forecasting future body poses based on observed pose sequences. This task is complex due to modeling spatial and temporal relationships. The most commonly used models for this task are autoregressive models, such as recurrent neural networks (RNNs) or variants, and Transformer Networks. However, RNNs have several drawbacks, such as vanishing or exploding gradients. Other researchers have attempted to solve the communication problem in the spatial dimension by integrating Graph Convolutional Networks (GCN) an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04956","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/2304.04956/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":"2304.04956","created_at":"2026-07-05T05:59:53.518152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04956v1","created_at":"2026-07-05T05:59:53.518152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04956","created_at":"2026-07-05T05:59:53.518152+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCM4TXRD3Q63","created_at":"2026-07-05T05:59:53.518152+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCM4TXRD3Q63BRVR","created_at":"2026-07-05T05:59:53.518152+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCM4TXRD","created_at":"2026-07-05T05:59:53.518152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11632","citing_title":"Multi-Scale Incremental Modeling for Enhanced Human Motion Prediction in Human-Robot Collaboration","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR","json":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR.json","graph_json":"https://pith.science/api/pith-number/TCM4TXRD3Q63BRVRPCO6X6PEMR/graph.json","events_json":"https://pith.science/api/pith-number/TCM4TXRD3Q63BRVRPCO6X6PEMR/events.json","paper":"https://pith.science/paper/TCM4TXRD"},"agent_actions":{"view_html":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR","download_json":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR.json","view_paper":"https://pith.science/paper/TCM4TXRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04956&json=true","fetch_graph":"https://pith.science/api/pith-number/TCM4TXRD3Q63BRVRPCO6X6PEMR/graph.json","fetch_events":"https://pith.science/api/pith-number/TCM4TXRD3Q63BRVRPCO6X6PEMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR/action/storage_attestation","attest_author":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR/action/author_attestation","sign_citation":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR/action/citation_signature","submit_replication":"https://pith.science/pith/TCM4TXRD3Q63BRVRPCO6X6PEMR/action/replication_record"}},"created_at":"2026-07-05T05:59:53.518152+00:00","updated_at":"2026-07-05T05:59:53.518152+00:00"}