{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AMYOU75KV7PUER66A45TQWMPWM","short_pith_number":"pith:AMYOU75K","schema_version":"1.0","canonical_sha256":"0330ea7faaafdf4247de073b38598fb307b79d8b9fcd7ad8f1acabdd7db31b13","source":{"kind":"arxiv","id":"2111.11433","version":1},"attestation_state":"computed","paper":{"title":"Towards Tokenized Human Dynamics Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyun Wei, Kenneth Li, Stephen Lin, Xiao Sun, Zhirong Wu","submitted_at":"2021-11-22T18:59:58Z","abstract_excerpt":"For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking. However, methods for understanding short semantic actions cannot be directly translated to long human dynamics such as dancing, where it becomes challenging even to label the human movements semantically. Meanwhile, the natural language processing (NLP) community has made progress in solving a similar challenge of annotation scarcity by large-scale pre-training, which improves several downstream tasks with one model. In this work, we stud"},"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":"2111.11433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-22T18:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"b7ca795c57232f267c118ecdc03b9183e914f0dad59d34d69139b5d2a1427dba","abstract_canon_sha256":"552d67a65c0b3f1dd70f9ff8093985bfdfc21279f6a8c73021b2ec87ddfd53c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:03.678418Z","signature_b64":"GM9cc870N71dXpfnxjJopPeMkto3KmdGQPgr7W8elvq9GWFfYwjQo+LwwfqQnzSSAMogTp4e+828w/NEfFL5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0330ea7faaafdf4247de073b38598fb307b79d8b9fcd7ad8f1acabdd7db31b13","last_reissued_at":"2026-07-05T03:34:03.677928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:03.677928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Tokenized Human Dynamics Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyun Wei, Kenneth Li, Stephen Lin, Xiao Sun, Zhirong Wu","submitted_at":"2021-11-22T18:59:58Z","abstract_excerpt":"For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking. However, methods for understanding short semantic actions cannot be directly translated to long human dynamics such as dancing, where it becomes challenging even to label the human movements semantically. Meanwhile, the natural language processing (NLP) community has made progress in solving a similar challenge of annotation scarcity by large-scale pre-training, which improves several downstream tasks with one model. In this work, we stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11433","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/2111.11433/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":"2111.11433","created_at":"2026-07-05T03:34:03.677983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11433v1","created_at":"2026-07-05T03:34:03.677983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11433","created_at":"2026-07-05T03:34:03.677983+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMYOU75KV7PU","created_at":"2026-07-05T03:34:03.677983+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMYOU75KV7PUER66","created_at":"2026-07-05T03:34:03.677983+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMYOU75K","created_at":"2026-07-05T03:34:03.677983+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/AMYOU75KV7PUER66A45TQWMPWM","json":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM.json","graph_json":"https://pith.science/api/pith-number/AMYOU75KV7PUER66A45TQWMPWM/graph.json","events_json":"https://pith.science/api/pith-number/AMYOU75KV7PUER66A45TQWMPWM/events.json","paper":"https://pith.science/paper/AMYOU75K"},"agent_actions":{"view_html":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM","download_json":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM.json","view_paper":"https://pith.science/paper/AMYOU75K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11433&json=true","fetch_graph":"https://pith.science/api/pith-number/AMYOU75KV7PUER66A45TQWMPWM/graph.json","fetch_events":"https://pith.science/api/pith-number/AMYOU75KV7PUER66A45TQWMPWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM/action/storage_attestation","attest_author":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM/action/author_attestation","sign_citation":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM/action/citation_signature","submit_replication":"https://pith.science/pith/AMYOU75KV7PUER66A45TQWMPWM/action/replication_record"}},"created_at":"2026-07-05T03:34:03.677983+00:00","updated_at":"2026-07-05T03:34:03.677983+00:00"}