{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XV7YC23LMIPCOWDT7CY3QBBD23","short_pith_number":"pith:XV7YC23L","schema_version":"1.0","canonical_sha256":"bd7f816b6b621e275873f8b1b80423d6e18947956105bccf013b463769c4f349","source":{"kind":"arxiv","id":"2405.10266","version":1},"attestation_state":"computed","paper":{"title":"A Tale of Two Languages: Large-Vocabulary Continuous Sign Language Recognition from Spoken Language Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Charles Raude, G\\\"ul Varol, Hannah Bull, K R Prajwal, Liliane Momeni, Samuel Albanie","submitted_at":"2024-05-16T17:19:06Z","abstract_excerpt":"In this work, our goals are two fold: large-vocabulary continuous sign language recognition (CSLR), and sign language retrieval. To this end, we introduce a multi-task Transformer model, CSLR2, that is able to ingest a signing sequence and output in a joint embedding space between signed language and spoken language text. To enable CSLR evaluation in the large-vocabulary setting, we introduce new dataset annotations that have been manually collected. These provide continuous sign-level annotations for six hours of test videos, and will be made publicly available. We demonstrate that by a caref"},"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":"2405.10266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T17:19:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b0189022f3960e515f1d545de389d0753e84fa115e12ff9fd4b0fa1062073d9b","abstract_canon_sha256":"61b462fda605f2c39616b5d926473e20e9b15fbd91050923c5199e5ce4000187"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:55.445745Z","signature_b64":"eo/YYENgS3XKGJfeEUfiMXDGk1iOddLkT+vaBjJk1jPyOaF2GFOv1XOK/stYr1CUF5knEca1SLtdCoOvmBCBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd7f816b6b621e275873f8b1b80423d6e18947956105bccf013b463769c4f349","last_reissued_at":"2026-07-05T08:19:55.445272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:55.445272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tale of Two Languages: Large-Vocabulary Continuous Sign Language Recognition from Spoken Language Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Charles Raude, G\\\"ul Varol, Hannah Bull, K R Prajwal, Liliane Momeni, Samuel Albanie","submitted_at":"2024-05-16T17:19:06Z","abstract_excerpt":"In this work, our goals are two fold: large-vocabulary continuous sign language recognition (CSLR), and sign language retrieval. To this end, we introduce a multi-task Transformer model, CSLR2, that is able to ingest a signing sequence and output in a joint embedding space between signed language and spoken language text. To enable CSLR evaluation in the large-vocabulary setting, we introduce new dataset annotations that have been manually collected. These provide continuous sign-level annotations for six hours of test videos, and will be made publicly available. We demonstrate that by a caref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10266","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/2405.10266/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":"2405.10266","created_at":"2026-07-05T08:19:55.445343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10266v1","created_at":"2026-07-05T08:19:55.445343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10266","created_at":"2026-07-05T08:19:55.445343+00:00"},{"alias_kind":"pith_short_12","alias_value":"XV7YC23LMIPC","created_at":"2026-07-05T08:19:55.445343+00:00"},{"alias_kind":"pith_short_16","alias_value":"XV7YC23LMIPCOWDT","created_at":"2026-07-05T08:19:55.445343+00:00"},{"alias_kind":"pith_short_8","alias_value":"XV7YC23L","created_at":"2026-07-05T08:19:55.445343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11332","citing_title":"Gloss-Free Representation Learning for Cross-Dataset Sign Spotting","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23","json":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23.json","graph_json":"https://pith.science/api/pith-number/XV7YC23LMIPCOWDT7CY3QBBD23/graph.json","events_json":"https://pith.science/api/pith-number/XV7YC23LMIPCOWDT7CY3QBBD23/events.json","paper":"https://pith.science/paper/XV7YC23L"},"agent_actions":{"view_html":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23","download_json":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23.json","view_paper":"https://pith.science/paper/XV7YC23L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10266&json=true","fetch_graph":"https://pith.science/api/pith-number/XV7YC23LMIPCOWDT7CY3QBBD23/graph.json","fetch_events":"https://pith.science/api/pith-number/XV7YC23LMIPCOWDT7CY3QBBD23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23/action/storage_attestation","attest_author":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23/action/author_attestation","sign_citation":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23/action/citation_signature","submit_replication":"https://pith.science/pith/XV7YC23LMIPCOWDT7CY3QBBD23/action/replication_record"}},"created_at":"2026-07-05T08:19:55.445343+00:00","updated_at":"2026-07-05T08:19:55.445343+00:00"}