{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEZVWMNBVTKOQNZKCBFTGD7LCU","short_pith_number":"pith:YEZVWMNB","schema_version":"1.0","canonical_sha256":"c1335b31a1acd4e8372a104b330feb153d90d4bdfbbc6d0d99b4c577646fac59","source":{"kind":"arxiv","id":"2403.12556","version":1},"attestation_state":"computed","paper":{"title":"Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjia Zhou, Guoqing Zhao, Jun Li, Jun Wan, Ning Jiang, Quan Lu, Zhen Lei, Zhigang Chen","submitted_at":"2024-03-19T09:00:23Z","abstract_excerpt":"Previous Sign Language Translation (SLT) methods achieve superior performance by relying on gloss annotations. However, labeling high-quality glosses is a labor-intensive task, which limits the further development of SLT. Although some approaches work towards gloss-free SLT through jointly training the visual encoder and translation network, these efforts still suffer from poor performance and inefficient use of the powerful Large Language Model (LLM). Most seriously, we find that directly introducing LLM into SLT will lead to insufficient learning of visual representations as LLM dominates th"},"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":"2403.12556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T09:00:23Z","cross_cats_sorted":[],"title_canon_sha256":"6a2d3d962ff4527c66a674b2de0e6689339010e99b3ad0fa3b1b839a421a5c1a","abstract_canon_sha256":"7d3c14ecad64ae309726179f99fc2a4b53832780ae4c239f08ba45f6c109888b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:03.490737Z","signature_b64":"abLKW71OIJbyGH6Z9/pEfRy6c+SlEcBbJPOdrWbt07CeQFWTmCTaRj886EihlQ7zCmQHG+HnjGd8Rz48Xi5KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1335b31a1acd4e8372a104b330feb153d90d4bdfbbc6d0d99b4c577646fac59","last_reissued_at":"2026-07-05T07:58:03.490183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:03.490183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjia Zhou, Guoqing Zhao, Jun Li, Jun Wan, Ning Jiang, Quan Lu, Zhen Lei, Zhigang Chen","submitted_at":"2024-03-19T09:00:23Z","abstract_excerpt":"Previous Sign Language Translation (SLT) methods achieve superior performance by relying on gloss annotations. However, labeling high-quality glosses is a labor-intensive task, which limits the further development of SLT. Although some approaches work towards gloss-free SLT through jointly training the visual encoder and translation network, these efforts still suffer from poor performance and inefficient use of the powerful Large Language Model (LLM). Most seriously, we find that directly introducing LLM into SLT will lead to insufficient learning of visual representations as LLM dominates th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12556","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/2403.12556/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":"2403.12556","created_at":"2026-07-05T07:58:03.490243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12556v1","created_at":"2026-07-05T07:58:03.490243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12556","created_at":"2026-07-05T07:58:03.490243+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEZVWMNBVTKO","created_at":"2026-07-05T07:58:03.490243+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEZVWMNBVTKOQNZK","created_at":"2026-07-05T07:58:03.490243+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEZVWMNB","created_at":"2026-07-05T07:58:03.490243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":241,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22374","citing_title":"Selective Contrastive Learning For Gloss Free Sign Language Translation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU","json":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU.json","graph_json":"https://pith.science/api/pith-number/YEZVWMNBVTKOQNZKCBFTGD7LCU/graph.json","events_json":"https://pith.science/api/pith-number/YEZVWMNBVTKOQNZKCBFTGD7LCU/events.json","paper":"https://pith.science/paper/YEZVWMNB"},"agent_actions":{"view_html":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU","download_json":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU.json","view_paper":"https://pith.science/paper/YEZVWMNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12556&json=true","fetch_graph":"https://pith.science/api/pith-number/YEZVWMNBVTKOQNZKCBFTGD7LCU/graph.json","fetch_events":"https://pith.science/api/pith-number/YEZVWMNBVTKOQNZKCBFTGD7LCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU/action/storage_attestation","attest_author":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU/action/author_attestation","sign_citation":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU/action/citation_signature","submit_replication":"https://pith.science/pith/YEZVWMNBVTKOQNZKCBFTGD7LCU/action/replication_record"}},"created_at":"2026-07-05T07:58:03.490243+00:00","updated_at":"2026-07-05T07:58:03.490243+00:00"}