{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UEL364KUX3XWGUSW42FGJHSGVN","short_pith_number":"pith:UEL364KU","schema_version":"1.0","canonical_sha256":"a117bf7154beef635256e68a649e46ab5f703a5554a97eb859213ad13960a6fd","source":{"kind":"arxiv","id":"2407.11855","version":1},"attestation_state":"computed","paper":{"title":"Scaling Sign Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Garrett Tanzer, Orhan Firat","submitted_at":"2024-07-16T15:36:58Z","abstract_excerpt":"Sign language translation (SLT) addresses the problem of translating information from a sign language in video to a spoken language in text. Existing studies, while showing progress, are often limited to narrow domains and/or few sign languages and struggle with open-domain tasks. In this paper, we push forward the frontier of SLT by scaling pretraining data, model size, and number of translation directions. We perform large-scale SLT pretraining on different data including 1) noisy multilingual YouTube SLT data, 2) parallel text corpora, and 3) SLT data augmented by translating video captions"},"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":"2407.11855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T15:36:58Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"3c6a87a8dfbac7d68b45b5d20586f43902d9af7719c09e09de5a3757fbb5f7ac","abstract_canon_sha256":"5545d927fd84a54d0dcf4917b84dc5ebe968001196ac64dbad6288941b98e3f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:41.606073Z","signature_b64":"2OysLDgsk7O+aEBqjlWskwNUePcIdNE7NSU220ZicsRXwMJb+TZTwW8pLZ4pcYsNBDQuJu7A0Z2BKatNDRTkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a117bf7154beef635256e68a649e46ab5f703a5554a97eb859213ad13960a6fd","last_reissued_at":"2026-07-05T08:44:41.605508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:41.605508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Sign Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Garrett Tanzer, Orhan Firat","submitted_at":"2024-07-16T15:36:58Z","abstract_excerpt":"Sign language translation (SLT) addresses the problem of translating information from a sign language in video to a spoken language in text. Existing studies, while showing progress, are often limited to narrow domains and/or few sign languages and struggle with open-domain tasks. In this paper, we push forward the frontier of SLT by scaling pretraining data, model size, and number of translation directions. We perform large-scale SLT pretraining on different data including 1) noisy multilingual YouTube SLT data, 2) parallel text corpora, and 3) SLT data augmented by translating video captions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11855","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/2407.11855/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":"2407.11855","created_at":"2026-07-05T08:44:41.605582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11855v1","created_at":"2026-07-05T08:44:41.605582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11855","created_at":"2026-07-05T08:44:41.605582+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEL364KUX3XW","created_at":"2026-07-05T08:44:41.605582+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEL364KUX3XWGUSW","created_at":"2026-07-05T08:44:41.605582+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEL364KU","created_at":"2026-07-05T08:44:41.605582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN","json":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN.json","graph_json":"https://pith.science/api/pith-number/UEL364KUX3XWGUSW42FGJHSGVN/graph.json","events_json":"https://pith.science/api/pith-number/UEL364KUX3XWGUSW42FGJHSGVN/events.json","paper":"https://pith.science/paper/UEL364KU"},"agent_actions":{"view_html":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN","download_json":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN.json","view_paper":"https://pith.science/paper/UEL364KU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11855&json=true","fetch_graph":"https://pith.science/api/pith-number/UEL364KUX3XWGUSW42FGJHSGVN/graph.json","fetch_events":"https://pith.science/api/pith-number/UEL364KUX3XWGUSW42FGJHSGVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN/action/storage_attestation","attest_author":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN/action/author_attestation","sign_citation":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN/action/citation_signature","submit_replication":"https://pith.science/pith/UEL364KUX3XWGUSW42FGJHSGVN/action/replication_record"}},"created_at":"2026-07-05T08:44:41.605582+00:00","updated_at":"2026-07-05T08:44:41.605582+00:00"}