{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J6HT2TFJVVIY6R7XQLD2V7QRB2","short_pith_number":"pith:J6HT2TFJ","schema_version":"1.0","canonical_sha256":"4f8f3d4ca9ad518f47f782c7aafe110e8eb11c3b4817fa6bc2dd75cf98651758","source":{"kind":"arxiv","id":"2305.01778","version":1},"attestation_state":"computed","paper":{"title":"SLTUNET: A Simple Unified Model for Sign Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Mathias M\\\"uller, Rico Sennrich","submitted_at":"2023-05-02T20:41:59Z","abstract_excerpt":"Despite recent successes with neural models for sign language translation (SLT), translation quality still lags behind spoken languages because of the data scarcity and modality gap between sign video and text. To address both problems, we investigate strategies for cross-modality representation sharing for SLT. We propose SLTUNET, a simple unified neural model designed to support multiple SLTrelated tasks jointly, such as sign-to-gloss, gloss-to-text and sign-to-text translation. Jointly modeling different tasks endows SLTUNET with the capability to explore the cross-task relatedness that cou"},"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":"2305.01778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-02T20:41:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"89df9b6fc167936eee0c2b7d10a89ba6c9bcdc0f794d1c523d6b2ee4da45769b","abstract_canon_sha256":"bdb0334291665d45b6fc7de032449ca5d63f5881916b2438cfb601e786610253"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:32.222889Z","signature_b64":"ErntOMgStviUcHxUWHVu5OmOFfRBDSaPL8fZVHgF0m4MmRoubVzY7AQEbVatqFqp54s4IY3P5w/NkRUhVZANBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f8f3d4ca9ad518f47f782c7aafe110e8eb11c3b4817fa6bc2dd75cf98651758","last_reissued_at":"2026-07-05T06:06:32.222556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:32.222556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLTUNET: A Simple Unified Model for Sign Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Mathias M\\\"uller, Rico Sennrich","submitted_at":"2023-05-02T20:41:59Z","abstract_excerpt":"Despite recent successes with neural models for sign language translation (SLT), translation quality still lags behind spoken languages because of the data scarcity and modality gap between sign video and text. To address both problems, we investigate strategies for cross-modality representation sharing for SLT. We propose SLTUNET, a simple unified neural model designed to support multiple SLTrelated tasks jointly, such as sign-to-gloss, gloss-to-text and sign-to-text translation. Jointly modeling different tasks endows SLTUNET with the capability to explore the cross-task relatedness that cou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01778","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/2305.01778/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":"2305.01778","created_at":"2026-07-05T06:06:32.222612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01778v1","created_at":"2026-07-05T06:06:32.222612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01778","created_at":"2026-07-05T06:06:32.222612+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6HT2TFJVVIY","created_at":"2026-07-05T06:06:32.222612+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6HT2TFJVVIY6R7X","created_at":"2026-07-05T06:06:32.222612+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6HT2TFJ","created_at":"2026-07-05T06:06:32.222612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03788","citing_title":"SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19352","citing_title":"Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards","ref_index":234,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2","json":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2.json","graph_json":"https://pith.science/api/pith-number/J6HT2TFJVVIY6R7XQLD2V7QRB2/graph.json","events_json":"https://pith.science/api/pith-number/J6HT2TFJVVIY6R7XQLD2V7QRB2/events.json","paper":"https://pith.science/paper/J6HT2TFJ"},"agent_actions":{"view_html":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2","download_json":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2.json","view_paper":"https://pith.science/paper/J6HT2TFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01778&json=true","fetch_graph":"https://pith.science/api/pith-number/J6HT2TFJVVIY6R7XQLD2V7QRB2/graph.json","fetch_events":"https://pith.science/api/pith-number/J6HT2TFJVVIY6R7XQLD2V7QRB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2/action/storage_attestation","attest_author":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2/action/author_attestation","sign_citation":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2/action/citation_signature","submit_replication":"https://pith.science/pith/J6HT2TFJVVIY6R7XQLD2V7QRB2/action/replication_record"}},"created_at":"2026-07-05T06:06:32.222612+00:00","updated_at":"2026-07-05T06:06:32.222612+00:00"}