{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJLUVG5WFD7BXU26JTJBPQUQ2B","short_pith_number":"pith:BJLUVG5W","schema_version":"1.0","canonical_sha256":"0a574a9bb628fe1bd35e4cd217c290d0738728a041dbc47f2f02d68cbb78d81c","source":{"kind":"arxiv","id":"2403.10434","version":3},"attestation_state":"computed","paper":{"title":"Spotter+GPT: Turning Sign Spottings into Sentences with LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ozge Mercanoglu Sincan, Richard Bowden","submitted_at":"2024-03-15T16:14:34Z","abstract_excerpt":"Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos. In this paper, we introduce a lightweight, modular SLT framework, Spotter+GPT, that leverages the power of Large Language Models (LLMs) and avoids heavy end-to-end training. Spotter+GPT breaks down the SLT task into two distinct stages. First, a sign spotter identifies individual signs within the input video. The spotted signs are then passed to an LLM, which transforms them into meaningful spoken language sentences. Spotter+GPT eliminates the requirement for SLT-spe"},"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":"2403.10434","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T16:14:34Z","cross_cats_sorted":[],"title_canon_sha256":"25ef41ac816aa15d79adca384d51f60c79ee9390123afeacee0d774561fda8a6","abstract_canon_sha256":"60808796c0e73b841e77bca42f746af6cf62f9269ea13ad4a5d9b35e02218d90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:59.742306Z","signature_b64":"r+RtIQG3cnK98aY54u2SSIUzhxEkZScqC/JwCnygpOo7ihYL71WQyBNMoFYYoOKZ/VKaOOa2ng4UpMVx/KvzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a574a9bb628fe1bd35e4cd217c290d0738728a041dbc47f2f02d68cbb78d81c","last_reissued_at":"2026-07-05T11:51:59.741799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:59.741799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spotter+GPT: Turning Sign Spottings into Sentences with LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ozge Mercanoglu Sincan, Richard Bowden","submitted_at":"2024-03-15T16:14:34Z","abstract_excerpt":"Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos. In this paper, we introduce a lightweight, modular SLT framework, Spotter+GPT, that leverages the power of Large Language Models (LLMs) and avoids heavy end-to-end training. Spotter+GPT breaks down the SLT task into two distinct stages. First, a sign spotter identifies individual signs within the input video. The spotted signs are then passed to an LLM, which transforms them into meaningful spoken language sentences. Spotter+GPT eliminates the requirement for SLT-spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10434","kind":"arxiv","version":3},"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/2403.10434/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":"2403.10434","created_at":"2026-07-05T11:51:59.741857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10434v3","created_at":"2026-07-05T11:51:59.741857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10434","created_at":"2026-07-05T11:51:59.741857+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJLUVG5WFD7B","created_at":"2026-07-05T11:51:59.741857+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJLUVG5WFD7BXU26","created_at":"2026-07-05T11:51:59.741857+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJLUVG5W","created_at":"2026-07-05T11:51:59.741857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10306","citing_title":"Contrastive Pretraining with Dual Visual Encoders for Gloss-Free Sign Language Translation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B","json":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B.json","graph_json":"https://pith.science/api/pith-number/BJLUVG5WFD7BXU26JTJBPQUQ2B/graph.json","events_json":"https://pith.science/api/pith-number/BJLUVG5WFD7BXU26JTJBPQUQ2B/events.json","paper":"https://pith.science/paper/BJLUVG5W"},"agent_actions":{"view_html":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B","download_json":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B.json","view_paper":"https://pith.science/paper/BJLUVG5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10434&json=true","fetch_graph":"https://pith.science/api/pith-number/BJLUVG5WFD7BXU26JTJBPQUQ2B/graph.json","fetch_events":"https://pith.science/api/pith-number/BJLUVG5WFD7BXU26JTJBPQUQ2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B/action/storage_attestation","attest_author":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B/action/author_attestation","sign_citation":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B/action/citation_signature","submit_replication":"https://pith.science/pith/BJLUVG5WFD7BXU26JTJBPQUQ2B/action/replication_record"}},"created_at":"2026-07-05T11:51:59.741857+00:00","updated_at":"2026-07-05T11:51:59.741857+00:00"}