{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IRURR2RVAXJPTBPKJFGIK743MM","short_pith_number":"pith:IRURR2RV","schema_version":"1.0","canonical_sha256":"446918ea3505d2f985ea494c857f9b6317350a79daf3975245b6a3347b864e88","source":{"kind":"arxiv","id":"2207.09644","version":3},"attestation_state":"computed","paper":{"title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Jianbo Yuan, Ligong Han, Long Zhao, Shijie Geng, Yu Tian, Yuxiao Chen, Zhaoyang Xia","submitted_at":"2022-07-20T04:21:05Z","abstract_excerpt":"Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at large scales is difficult. Recent studies focus on learning video-level temporal and discriminative information using contrastive learning, but overlook the hierarchical spatial-temporal nature of human skeletons. Different from such superficial supervision at the video level, we propose a self-supervised hierarchical pre-training scheme incorporated into a "},"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":"2207.09644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T04:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"c73a1125e450042a41327a811cef5223676277ab5bce7d70ecdbec897ea9c30a","abstract_canon_sha256":"6a921f3d237ee71f238022e907862e88415a713e1560533fda965a91b26865c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:54.480241Z","signature_b64":"vb6RV02uPgIrlxwBqJcbY31TCfZheTHw8f3oqiqCawEbe3Bvtu6/94nGAZwmVyY80aV4bLrM4DOPfNnz+ebEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446918ea3505d2f985ea494c857f9b6317350a79daf3975245b6a3347b864e88","last_reissued_at":"2026-07-05T05:54:54.479812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:54.479812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Jianbo Yuan, Ligong Han, Long Zhao, Shijie Geng, Yu Tian, Yuxiao Chen, Zhaoyang Xia","submitted_at":"2022-07-20T04:21:05Z","abstract_excerpt":"Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at large scales is difficult. Recent studies focus on learning video-level temporal and discriminative information using contrastive learning, but overlook the hierarchical spatial-temporal nature of human skeletons. Different from such superficial supervision at the video level, we propose a self-supervised hierarchical pre-training scheme incorporated into a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09644","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/2207.09644/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":"2207.09644","created_at":"2026-07-05T05:54:54.479870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09644v3","created_at":"2026-07-05T05:54:54.479870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09644","created_at":"2026-07-05T05:54:54.479870+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRURR2RVAXJP","created_at":"2026-07-05T05:54:54.479870+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRURR2RVAXJPTBPK","created_at":"2026-07-05T05:54:54.479870+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRURR2RV","created_at":"2026-07-05T05:54:54.479870+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/IRURR2RVAXJPTBPKJFGIK743MM","json":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM.json","graph_json":"https://pith.science/api/pith-number/IRURR2RVAXJPTBPKJFGIK743MM/graph.json","events_json":"https://pith.science/api/pith-number/IRURR2RVAXJPTBPKJFGIK743MM/events.json","paper":"https://pith.science/paper/IRURR2RV"},"agent_actions":{"view_html":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM","download_json":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM.json","view_paper":"https://pith.science/paper/IRURR2RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09644&json=true","fetch_graph":"https://pith.science/api/pith-number/IRURR2RVAXJPTBPKJFGIK743MM/graph.json","fetch_events":"https://pith.science/api/pith-number/IRURR2RVAXJPTBPKJFGIK743MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM/action/storage_attestation","attest_author":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM/action/author_attestation","sign_citation":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM/action/citation_signature","submit_replication":"https://pith.science/pith/IRURR2RVAXJPTBPKJFGIK743MM/action/replication_record"}},"created_at":"2026-07-05T05:54:54.479870+00:00","updated_at":"2026-07-05T05:54:54.479870+00:00"}