{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z7DQ66UN46HW3EYGWWOLXKW2MO","short_pith_number":"pith:Z7DQ66UN","schema_version":"1.0","canonical_sha256":"cfc70f7a8de78f6d9306b59cbbaada63891b02ca63a94de20c94f64cd4a368c7","source":{"kind":"arxiv","id":"2507.01532","version":1},"attestation_state":"computed","paper":{"title":"Exploring Pose-based Sign Language Translation: Ablation Studies and Attention Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Gruber, Jakub Straka, Marek Hruz, Ondrej Valach, Tomas Zelezny, Vaclav Javorek","submitted_at":"2025-07-02T09:36:26Z","abstract_excerpt":"Sign Language Translation (SLT) has evolved significantly, moving from isolated recognition approaches to complex, continuous gloss-free translation systems. This paper explores the impact of pose-based data preprocessing techniques - normalization, interpolation, and augmentation - on SLT performance. We employ a transformer-based architecture, adapting a modified T5 encoder-decoder model to process pose representations. Through extensive ablation studies on YouTubeASL and How2Sign datasets, we analyze how different preprocessing strategies affect translation accuracy. Our results demonstrate"},"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":"2507.01532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T09:36:26Z","cross_cats_sorted":[],"title_canon_sha256":"7fdd9a5fab7fd8804c75ead812aaa305da7452d7d97a0a56f1a3eaa651f44e6b","abstract_canon_sha256":"71b5b2ed1400734448b8bbb5cf91999a3b0bc9fae55c4a6fb0f9f1c08a2f4528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:50.453172Z","signature_b64":"AhgSfClN/TeG/llE3K9KhhZqZ/AlDHAbZBmpsaKPtkPe5TUMurVbMAiKh8Mer8aCzLR8Xk8/dsFCh/u/joXFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc70f7a8de78f6d9306b59cbbaada63891b02ca63a94de20c94f64cd4a368c7","last_reissued_at":"2026-07-05T11:30:50.452678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:50.452678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Pose-based Sign Language Translation: Ablation Studies and Attention Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Gruber, Jakub Straka, Marek Hruz, Ondrej Valach, Tomas Zelezny, Vaclav Javorek","submitted_at":"2025-07-02T09:36:26Z","abstract_excerpt":"Sign Language Translation (SLT) has evolved significantly, moving from isolated recognition approaches to complex, continuous gloss-free translation systems. This paper explores the impact of pose-based data preprocessing techniques - normalization, interpolation, and augmentation - on SLT performance. We employ a transformer-based architecture, adapting a modified T5 encoder-decoder model to process pose representations. Through extensive ablation studies on YouTubeASL and How2Sign datasets, we analyze how different preprocessing strategies affect translation accuracy. Our results demonstrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01532","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/2507.01532/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":"2507.01532","created_at":"2026-07-05T11:30:50.452738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01532v1","created_at":"2026-07-05T11:30:50.452738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01532","created_at":"2026-07-05T11:30:50.452738+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7DQ66UN46HW","created_at":"2026-07-05T11:30:50.452738+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7DQ66UN46HW3EYG","created_at":"2026-07-05T11:30:50.452738+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7DQ66UN","created_at":"2026-07-05T11:30:50.452738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31393","citing_title":"Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO","json":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO.json","graph_json":"https://pith.science/api/pith-number/Z7DQ66UN46HW3EYGWWOLXKW2MO/graph.json","events_json":"https://pith.science/api/pith-number/Z7DQ66UN46HW3EYGWWOLXKW2MO/events.json","paper":"https://pith.science/paper/Z7DQ66UN"},"agent_actions":{"view_html":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO","download_json":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO.json","view_paper":"https://pith.science/paper/Z7DQ66UN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01532&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7DQ66UN46HW3EYGWWOLXKW2MO/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7DQ66UN46HW3EYGWWOLXKW2MO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO/action/storage_attestation","attest_author":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO/action/author_attestation","sign_citation":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO/action/citation_signature","submit_replication":"https://pith.science/pith/Z7DQ66UN46HW3EYGWWOLXKW2MO/action/replication_record"}},"created_at":"2026-07-05T11:30:50.452738+00:00","updated_at":"2026-07-05T11:30:50.452738+00:00"}