{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XCYI636NEVQTLSJ7AQQ5GOTOLF","short_pith_number":"pith:XCYI636N","schema_version":"1.0","canonical_sha256":"b8b08f6fcd256135c93f0421d33a6e597a407b9e77da161fe79534e1d2252de7","source":{"kind":"arxiv","id":"2407.01394","version":2},"attestation_state":"computed","paper":{"title":"Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonios Anastasopoulos, Jana Ko\\v{s}eck\\'a, Pooya Fayyazsanavi","submitted_at":"2024-07-01T15:46:45Z","abstract_excerpt":"Sign language translation from video to spoken text presents unique challenges owing to the distinct grammar, expression nuances, and high variation of visual appearance across different speakers and contexts. The intermediate gloss annotations of videos aim to guide the translation process. In our work, we focus on {\\em Gloss2Text} translation stage and propose several advances by leveraging pre-trained large language models (LLMs), data augmentation, and novel label-smoothing loss function exploiting gloss translation ambiguities improving significantly the performance of state-of-the-art ap"},"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":"2407.01394","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T15:46:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0f4682da1c47ae6a87a7b992d90a6b5572a0c3f4174cd949bfc7b740e8e92fa5","abstract_canon_sha256":"0b5d52066d6545e22c594d89a793071f24a35db81cd55804d32e194fb0b6de6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:11.349661Z","signature_b64":"n6dUg2JYrmbo3CQdKuLObH1+4ymDcWYkDnlqQ4jcctN2r9m53XyKOupm5sjyq42RPXskuNbO0XFonMEDUheACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b08f6fcd256135c93f0421d33a6e597a407b9e77da161fe79534e1d2252de7","last_reissued_at":"2026-07-05T08:43:11.349182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:11.349182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonios Anastasopoulos, Jana Ko\\v{s}eck\\'a, Pooya Fayyazsanavi","submitted_at":"2024-07-01T15:46:45Z","abstract_excerpt":"Sign language translation from video to spoken text presents unique challenges owing to the distinct grammar, expression nuances, and high variation of visual appearance across different speakers and contexts. The intermediate gloss annotations of videos aim to guide the translation process. In our work, we focus on {\\em Gloss2Text} translation stage and propose several advances by leveraging pre-trained large language models (LLMs), data augmentation, and novel label-smoothing loss function exploiting gloss translation ambiguities improving significantly the performance of state-of-the-art ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01394","kind":"arxiv","version":2},"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/2407.01394/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":"2407.01394","created_at":"2026-07-05T08:43:11.349246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01394v2","created_at":"2026-07-05T08:43:11.349246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01394","created_at":"2026-07-05T08:43:11.349246+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCYI636NEVQT","created_at":"2026-07-05T08:43:11.349246+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCYI636NEVQTLSJ7","created_at":"2026-07-05T08:43:11.349246+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCYI636N","created_at":"2026-07-05T08:43:11.349246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18183","citing_title":"Leveraging Large Language Models for Accurate Sign Language Translation in Low-Resource Scenarios","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF","json":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF.json","graph_json":"https://pith.science/api/pith-number/XCYI636NEVQTLSJ7AQQ5GOTOLF/graph.json","events_json":"https://pith.science/api/pith-number/XCYI636NEVQTLSJ7AQQ5GOTOLF/events.json","paper":"https://pith.science/paper/XCYI636N"},"agent_actions":{"view_html":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF","download_json":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF.json","view_paper":"https://pith.science/paper/XCYI636N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01394&json=true","fetch_graph":"https://pith.science/api/pith-number/XCYI636NEVQTLSJ7AQQ5GOTOLF/graph.json","fetch_events":"https://pith.science/api/pith-number/XCYI636NEVQTLSJ7AQQ5GOTOLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF/action/storage_attestation","attest_author":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF/action/author_attestation","sign_citation":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF/action/citation_signature","submit_replication":"https://pith.science/pith/XCYI636NEVQTLSJ7AQQ5GOTOLF/action/replication_record"}},"created_at":"2026-07-05T08:43:11.349246+00:00","updated_at":"2026-07-05T08:43:11.349246+00:00"}