{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XFDP3U3AJ6GIRID2PUNYINCEVN","short_pith_number":"pith:XFDP3U3A","schema_version":"1.0","canonical_sha256":"b946fdd3604f8c88a07a7d1b843444ab7b54226357eecbfbcbb5bafadc6c501b","source":{"kind":"arxiv","id":"2501.15187","version":3},"attestation_state":"computed","paper":{"title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Houqiang Li, Kepeng Wu, Weichao Zhao, Wengang Zhou, Zecheng Li","submitted_at":"2025-01-25T11:51:23Z","abstract_excerpt":"Sign language pre-training has gained increasing attention for its ability to enhance performance across various sign language understanding (SLU) tasks. However, existing methods often suffer from a gap between pre-training and fine-tuning, leading to suboptimal results. To address this, we propose Uni-Sign, a unified pre-training framework that eliminates the gap between pre-training and downstream SLU tasks through a large-scale generative pre-training strategy and a novel fine-tuning paradigm. First, we introduce CSL-News, a large-scale Chinese Sign Language (CSL) dataset containing 1,985 "},"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":"2501.15187","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T11:51:23Z","cross_cats_sorted":[],"title_canon_sha256":"3de505de05710b5dd56b1cbd0a85ee99c26656bf8cf480cc0d6dc10749e1a69b","abstract_canon_sha256":"e87ef79d1b066387a7017af781ffbe18c5492465f95aecd3d156139b16a21f39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:30.469831Z","signature_b64":"2v3N4ZF9bxAt0jRKz4P1L4vlZnat7GUvvJX2EhoBZ8n/2NYZJL4fSPqZVUeeIXZn+aAXIxvsW55nCC7oyDqmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b946fdd3604f8c88a07a7d1b843444ab7b54226357eecbfbcbb5bafadc6c501b","last_reissued_at":"2026-07-05T10:30:30.469297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:30.469297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Houqiang Li, Kepeng Wu, Weichao Zhao, Wengang Zhou, Zecheng Li","submitted_at":"2025-01-25T11:51:23Z","abstract_excerpt":"Sign language pre-training has gained increasing attention for its ability to enhance performance across various sign language understanding (SLU) tasks. However, existing methods often suffer from a gap between pre-training and fine-tuning, leading to suboptimal results. To address this, we propose Uni-Sign, a unified pre-training framework that eliminates the gap between pre-training and downstream SLU tasks through a large-scale generative pre-training strategy and a novel fine-tuning paradigm. First, we introduce CSL-News, a large-scale Chinese Sign Language (CSL) dataset containing 1,985 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15187","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/2501.15187/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":"2501.15187","created_at":"2026-07-05T10:30:30.469369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15187v3","created_at":"2026-07-05T10:30:30.469369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15187","created_at":"2026-07-05T10:30:30.469369+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFDP3U3AJ6GI","created_at":"2026-07-05T10:30:30.469369+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFDP3U3AJ6GIRID2","created_at":"2026-07-05T10:30:30.469369+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFDP3U3A","created_at":"2026-07-05T10:30:30.469369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19352","citing_title":"Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04465","citing_title":"Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14705","citing_title":"Towards Continuous Sign Language Conversation from Isolated Signs","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15301","citing_title":"Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN","json":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN.json","graph_json":"https://pith.science/api/pith-number/XFDP3U3AJ6GIRID2PUNYINCEVN/graph.json","events_json":"https://pith.science/api/pith-number/XFDP3U3AJ6GIRID2PUNYINCEVN/events.json","paper":"https://pith.science/paper/XFDP3U3A"},"agent_actions":{"view_html":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN","download_json":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN.json","view_paper":"https://pith.science/paper/XFDP3U3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15187&json=true","fetch_graph":"https://pith.science/api/pith-number/XFDP3U3AJ6GIRID2PUNYINCEVN/graph.json","fetch_events":"https://pith.science/api/pith-number/XFDP3U3AJ6GIRID2PUNYINCEVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN/action/storage_attestation","attest_author":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN/action/author_attestation","sign_citation":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN/action/citation_signature","submit_replication":"https://pith.science/pith/XFDP3U3AJ6GIRID2PUNYINCEVN/action/replication_record"}},"created_at":"2026-07-05T10:30:30.469369+00:00","updated_at":"2026-07-05T10:30:30.469369+00:00"}