{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNEVRLVBABMI4LVVCYSD2ENUEF","short_pith_number":"pith:FNEVRLVB","schema_version":"1.0","canonical_sha256":"2b4958aea100588e2eb516243d11b4214466fb2c70eeddd5fef37edd3999328a","source":{"kind":"arxiv","id":"2404.00925","version":1},"attestation_state":"computed","paper":{"title":"LLMs are Good Sign Language Translators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hossein Rahmani, Jia Gong, Jun Liu, Lin Geng Foo, Yixuan He","submitted_at":"2024-04-01T05:07:13Z","abstract_excerpt":"Sign Language Translation (SLT) is a challenging task that aims to translate sign videos into spoken language. Inspired by the strong translation capabilities of large language models (LLMs) that are trained on extensive multilingual text corpora, we aim to harness off-the-shelf LLMs to handle SLT. In this paper, we regularize the sign videos to embody linguistic characteristics of spoken language, and propose a novel SignLLM framework to transform sign videos into a language-like representation for improved readability by off-the-shelf LLMs. SignLLM comprises two key modules: (1) The Vector-Q"},"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":"2404.00925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T05:07:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a4c761b62ccf701a55568bf8283dbaf5336aad9dac71eb17f7b2b7dd9fa8c105","abstract_canon_sha256":"e44ff561b75a48936b17213bd3bb8b52fbd56c01dddf17cf1ec25d6963d0f15a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:58.819999Z","signature_b64":"cd7qV8cPkE5EpTVB14sZlwMnPXjRf741/oSBvbzslxJCr8gfy8nCT6ssirdbhXbWzP+6+dSNdBytOtDGnWnADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b4958aea100588e2eb516243d11b4214466fb2c70eeddd5fef37edd3999328a","last_reissued_at":"2026-07-05T08:02:58.819406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:58.819406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs are Good Sign Language Translators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hossein Rahmani, Jia Gong, Jun Liu, Lin Geng Foo, Yixuan He","submitted_at":"2024-04-01T05:07:13Z","abstract_excerpt":"Sign Language Translation (SLT) is a challenging task that aims to translate sign videos into spoken language. Inspired by the strong translation capabilities of large language models (LLMs) that are trained on extensive multilingual text corpora, we aim to harness off-the-shelf LLMs to handle SLT. In this paper, we regularize the sign videos to embody linguistic characteristics of spoken language, and propose a novel SignLLM framework to transform sign videos into a language-like representation for improved readability by off-the-shelf LLMs. SignLLM comprises two key modules: (1) The Vector-Q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00925","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/2404.00925/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":"2404.00925","created_at":"2026-07-05T08:02:58.819474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00925v1","created_at":"2026-07-05T08:02:58.819474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00925","created_at":"2026-07-05T08:02:58.819474+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNEVRLVBABMI","created_at":"2026-07-05T08:02:58.819474+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNEVRLVBABMI4LVV","created_at":"2026-07-05T08:02:58.819474+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNEVRLVB","created_at":"2026-07-05T08:02:58.819474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00765","citing_title":"Beyond Words: AuralLLM and SignMST-C for Sign Language Production and Bidirectional Accessibility","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF","json":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF.json","graph_json":"https://pith.science/api/pith-number/FNEVRLVBABMI4LVVCYSD2ENUEF/graph.json","events_json":"https://pith.science/api/pith-number/FNEVRLVBABMI4LVVCYSD2ENUEF/events.json","paper":"https://pith.science/paper/FNEVRLVB"},"agent_actions":{"view_html":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF","download_json":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF.json","view_paper":"https://pith.science/paper/FNEVRLVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00925&json=true","fetch_graph":"https://pith.science/api/pith-number/FNEVRLVBABMI4LVVCYSD2ENUEF/graph.json","fetch_events":"https://pith.science/api/pith-number/FNEVRLVBABMI4LVVCYSD2ENUEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF/action/storage_attestation","attest_author":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF/action/author_attestation","sign_citation":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF/action/citation_signature","submit_replication":"https://pith.science/pith/FNEVRLVBABMI4LVVCYSD2ENUEF/action/replication_record"}},"created_at":"2026-07-05T08:02:58.819474+00:00","updated_at":"2026-07-05T08:02:58.819474+00:00"}