{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SF656JWO4AP6KBQJZV44TA5XBX","short_pith_number":"pith:SF656JWO","schema_version":"1.0","canonical_sha256":"917ddf26cee01fe50609cd79c983b70dc8529e2131cff3c4bcec35a3201271d1","source":{"kind":"arxiv","id":"2309.02450","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Video Transformers for Isolated Sign Language Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diane Brentari, Gregory Shakhnarovich, Karen Livescu, Marcelo Sandoval-Castaneda, Yanhong Li","submitted_at":"2023-09-02T03:00:03Z","abstract_excerpt":"This paper presents an in-depth analysis of various self-supervision methods for isolated sign language recognition (ISLR). We consider four recently introduced transformer-based approaches to self-supervised learning from videos, and four pre-training data regimes, and study all the combinations on the WLASL2000 dataset. Our findings reveal that MaskFeat achieves performance superior to pose-based and supervised video models, with a top-1 accuracy of 79.02% on gloss-based WLASL2000. Furthermore, we analyze these models' ability to produce representations of ASL signs using linear probing on d"},"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":"2309.02450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-02T03:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"46a4a6e8f784bb74821b153b95a1582c8bece69311111811eb52644bdac8556e","abstract_canon_sha256":"7b74e45048c519f424425b1c86a5d1f30ea3431583f44e404aa4f98b7359e6ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:12.393508Z","signature_b64":"+oL8SmRHhCn3o8IMinfN6D366f9BuvDVvvh8uG64/QhqNbSQaQF422xTPvtHwzSEWtL+wuH6YEdMFTfHddgqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917ddf26cee01fe50609cd79c983b70dc8529e2131cff3c4bcec35a3201271d1","last_reissued_at":"2026-07-05T06:48:12.392998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:12.392998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Video Transformers for Isolated Sign Language Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diane Brentari, Gregory Shakhnarovich, Karen Livescu, Marcelo Sandoval-Castaneda, Yanhong Li","submitted_at":"2023-09-02T03:00:03Z","abstract_excerpt":"This paper presents an in-depth analysis of various self-supervision methods for isolated sign language recognition (ISLR). We consider four recently introduced transformer-based approaches to self-supervised learning from videos, and four pre-training data regimes, and study all the combinations on the WLASL2000 dataset. Our findings reveal that MaskFeat achieves performance superior to pose-based and supervised video models, with a top-1 accuracy of 79.02% on gloss-based WLASL2000. Furthermore, we analyze these models' ability to produce representations of ASL signs using linear probing on d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02450","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/2309.02450/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":"2309.02450","created_at":"2026-07-05T06:48:12.393060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02450v1","created_at":"2026-07-05T06:48:12.393060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02450","created_at":"2026-07-05T06:48:12.393060+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF656JWO4AP6","created_at":"2026-07-05T06:48:12.393060+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF656JWO4AP6KBQJ","created_at":"2026-07-05T06:48:12.393060+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF656JWO","created_at":"2026-07-05T06:48:12.393060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27232","citing_title":"Targeted Linguistic Analysis of Sign Language Models with Minimal Translation Pairs","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX","json":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX.json","graph_json":"https://pith.science/api/pith-number/SF656JWO4AP6KBQJZV44TA5XBX/graph.json","events_json":"https://pith.science/api/pith-number/SF656JWO4AP6KBQJZV44TA5XBX/events.json","paper":"https://pith.science/paper/SF656JWO"},"agent_actions":{"view_html":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX","download_json":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX.json","view_paper":"https://pith.science/paper/SF656JWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02450&json=true","fetch_graph":"https://pith.science/api/pith-number/SF656JWO4AP6KBQJZV44TA5XBX/graph.json","fetch_events":"https://pith.science/api/pith-number/SF656JWO4AP6KBQJZV44TA5XBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX/action/storage_attestation","attest_author":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX/action/author_attestation","sign_citation":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX/action/citation_signature","submit_replication":"https://pith.science/pith/SF656JWO4AP6KBQJZV44TA5XBX/action/replication_record"}},"created_at":"2026-07-05T06:48:12.393060+00:00","updated_at":"2026-07-05T06:48:12.393060+00:00"}