{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K5AIHM5FE77SIER6I42TK4WEGP","short_pith_number":"pith:K5AIHM5F","schema_version":"1.0","canonical_sha256":"574083b3a527ff24123e47353572c433d363f0c67805a2d6e9785e4ec65e54f1","source":{"kind":"arxiv","id":"2410.20349","version":1},"attestation_state":"computed","paper":{"title":"Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahang Zhang, Jiaying Liu, Lehong Wu, Lilang Lin","submitted_at":"2024-10-27T06:29:04Z","abstract_excerpt":"Generative models, as a powerful technique for generation, also gradually become a critical tool for recognition tasks. However, in skeleton-based action recognition, the features obtained from existing pre-trained generative methods contain redundant information unrelated to recognition, which contradicts the nature of the skeleton's spatially sparse and temporally consistent properties, leading to undesirable performance. To address this challenge, we make efforts to bridge the gap in theory and methodology and propose a novel skeleton-based idempotent generative model (IGM) for unsupervised"},"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":"2410.20349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T06:29:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdf022d54f1e1904a5ef4ed93d7ad5437524b2c005b44f763665bae484735233","abstract_canon_sha256":"82c0b67a9206752dc71a325443c29fe9686957fc7c230c5d93579b56575ea858"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:43.593025Z","signature_b64":"q3Dpjff1JKTpWpi2l8a5kqv7OXTiTRh6HvOyIADHQ89485XWMZgmG4IfC0GPZfH6w3yy8y2UF/Dt3iD0k7uVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"574083b3a527ff24123e47353572c433d363f0c67805a2d6e9785e4ec65e54f1","last_reissued_at":"2026-07-05T09:26:43.592555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:43.592555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahang Zhang, Jiaying Liu, Lehong Wu, Lilang Lin","submitted_at":"2024-10-27T06:29:04Z","abstract_excerpt":"Generative models, as a powerful technique for generation, also gradually become a critical tool for recognition tasks. However, in skeleton-based action recognition, the features obtained from existing pre-trained generative methods contain redundant information unrelated to recognition, which contradicts the nature of the skeleton's spatially sparse and temporally consistent properties, leading to undesirable performance. To address this challenge, we make efforts to bridge the gap in theory and methodology and propose a novel skeleton-based idempotent generative model (IGM) for unsupervised"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20349","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/2410.20349/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":"2410.20349","created_at":"2026-07-05T09:26:43.592615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20349v1","created_at":"2026-07-05T09:26:43.592615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20349","created_at":"2026-07-05T09:26:43.592615+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5AIHM5FE77S","created_at":"2026-07-05T09:26:43.592615+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5AIHM5FE77SIER6","created_at":"2026-07-05T09:26:43.592615+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5AIHM5F","created_at":"2026-07-05T09:26:43.592615+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/K5AIHM5FE77SIER6I42TK4WEGP","json":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP.json","graph_json":"https://pith.science/api/pith-number/K5AIHM5FE77SIER6I42TK4WEGP/graph.json","events_json":"https://pith.science/api/pith-number/K5AIHM5FE77SIER6I42TK4WEGP/events.json","paper":"https://pith.science/paper/K5AIHM5F"},"agent_actions":{"view_html":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP","download_json":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP.json","view_paper":"https://pith.science/paper/K5AIHM5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20349&json=true","fetch_graph":"https://pith.science/api/pith-number/K5AIHM5FE77SIER6I42TK4WEGP/graph.json","fetch_events":"https://pith.science/api/pith-number/K5AIHM5FE77SIER6I42TK4WEGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP/action/storage_attestation","attest_author":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP/action/author_attestation","sign_citation":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP/action/citation_signature","submit_replication":"https://pith.science/pith/K5AIHM5FE77SIER6I42TK4WEGP/action/replication_record"}},"created_at":"2026-07-05T09:26:43.592615+00:00","updated_at":"2026-07-05T09:26:43.592615+00:00"}