{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DCLU4EHIMZUAYP6WC3HEFAIZUP","short_pith_number":"pith:DCLU4EHI","schema_version":"1.0","canonical_sha256":"18974e10e866680c3fd616ce428119a3e61ed777212ed6c9c4930931d0bc2cd3","source":{"kind":"arxiv","id":"2603.16943","version":2},"attestation_state":"computed","paper":{"title":"KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guofa Li, Jiaxin Gao, Jie Li, Liping Zhang, Wenbo Chu, Yicui Shi, Yuhan Chen","submitted_at":"2026-03-16T07:47:33Z","abstract_excerpt":"Skeleton-based action recognition is widely applied in sensor-based systems, including human-computer interaction and intelligent surveillance. However, typical sensors produce sparse and discrete joint coordinates, often leading to the loss of fine-grained spatiotemporal information during dynamic movements. Furthermore, predefined physical topologies restrict modeling potential long-range dependencies. To address these challenges, we propose KGS-GCN, which integrates kinematics-driven Gaussian splatting and probabilistic topology within a graph convolutional network. A Gaussian splatting mod"},"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":"2603.16943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-16T07:47:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a6f76b19675c1d42f0ecabd85dac643f85ecbcf0618ce761c5c52b8a93958db5","abstract_canon_sha256":"53a4233143bd782005c09f834e762f831a9ebf5660463cf117e89fde24e07591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:28.039961Z","signature_b64":"QPMAMViSGGOjy2c4yeET8/Jaev3PKvAyUSn4NNS5ny2uO9lMtsB13DIyGlf7c+UlS9OQlq8re7aCtOJfRWbkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18974e10e866680c3fd616ce428119a3e61ed777212ed6c9c4930931d0bc2cd3","last_reissued_at":"2026-07-02T00:18:28.039135Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:28.039135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guofa Li, Jiaxin Gao, Jie Li, Liping Zhang, Wenbo Chu, Yicui Shi, Yuhan Chen","submitted_at":"2026-03-16T07:47:33Z","abstract_excerpt":"Skeleton-based action recognition is widely applied in sensor-based systems, including human-computer interaction and intelligent surveillance. However, typical sensors produce sparse and discrete joint coordinates, often leading to the loss of fine-grained spatiotemporal information during dynamic movements. Furthermore, predefined physical topologies restrict modeling potential long-range dependencies. To address these challenges, we propose KGS-GCN, which integrates kinematics-driven Gaussian splatting and probabilistic topology within a graph convolutional network. A Gaussian splatting mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16943","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/2603.16943/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":"2603.16943","created_at":"2026-07-02T00:18:28.039250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.16943v2","created_at":"2026-07-02T00:18:28.039250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16943","created_at":"2026-07-02T00:18:28.039250+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCLU4EHIMZUA","created_at":"2026-07-02T00:18:28.039250+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCLU4EHIMZUAYP6W","created_at":"2026-07-02T00:18:28.039250+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCLU4EHI","created_at":"2026-07-02T00:18:28.039250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.17998","citing_title":"AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17985","citing_title":"Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP","json":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP.json","graph_json":"https://pith.science/api/pith-number/DCLU4EHIMZUAYP6WC3HEFAIZUP/graph.json","events_json":"https://pith.science/api/pith-number/DCLU4EHIMZUAYP6WC3HEFAIZUP/events.json","paper":"https://pith.science/paper/DCLU4EHI"},"agent_actions":{"view_html":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP","download_json":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP.json","view_paper":"https://pith.science/paper/DCLU4EHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.16943&json=true","fetch_graph":"https://pith.science/api/pith-number/DCLU4EHIMZUAYP6WC3HEFAIZUP/graph.json","fetch_events":"https://pith.science/api/pith-number/DCLU4EHIMZUAYP6WC3HEFAIZUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP/action/storage_attestation","attest_author":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP/action/author_attestation","sign_citation":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP/action/citation_signature","submit_replication":"https://pith.science/pith/DCLU4EHIMZUAYP6WC3HEFAIZUP/action/replication_record"}},"created_at":"2026-07-02T00:18:28.039250+00:00","updated_at":"2026-07-02T00:18:28.039250+00:00"}