{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZB6GSKYIBOJG3GAJEXKMFDQAD4","short_pith_number":"pith:ZB6GSKYI","schema_version":"1.0","canonical_sha256":"c87c692b080b926d980925d4c28e001f1bebedd2a3fb532b368e9b2c20df350f","source":{"kind":"arxiv","id":"2412.09014","version":4},"attestation_state":"computed","paper":{"title":"Improvement in Sign Language Translation Using Text CTC Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kazuhiro Nakadai, Nabeela Khan, Sihan Tan, Taro Miyazaki","submitted_at":"2024-12-12T07:24:16Z","abstract_excerpt":"Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken text. In this work, we propose a novel method combining joint CTC/Attention and transfer learning. The joint CTC/Attention introduces hierarchical encoding and integrates CTC with the attention mechanism during decoding, effectively managing both monotonic and non-monotonic alignments. Meanwhile, transfer learning helps bridge the modality gap between vision and"},"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":"2412.09014","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T07:24:16Z","cross_cats_sorted":[],"title_canon_sha256":"44d62548de85cd6d441e82254312172014efc2ebe010f522d198b2a0dc62dd58","abstract_canon_sha256":"2613648b4667a0969f06162f8a95e5d8c20f435a3d12338ea8c6838e460f4bbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:46.791001Z","signature_b64":"+DCWtNUWEamfhPyL+lN124FJZMcqlz+BYyHbL/BpEtXgOC12chMbkHQaPwmjVPlz9HTdGRUq8zM9eFPxomqZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c87c692b080b926d980925d4c28e001f1bebedd2a3fb532b368e9b2c20df350f","last_reissued_at":"2026-07-05T09:53:46.790521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:46.790521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improvement in Sign Language Translation Using Text CTC Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kazuhiro Nakadai, Nabeela Khan, Sihan Tan, Taro Miyazaki","submitted_at":"2024-12-12T07:24:16Z","abstract_excerpt":"Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken text. In this work, we propose a novel method combining joint CTC/Attention and transfer learning. The joint CTC/Attention introduces hierarchical encoding and integrates CTC with the attention mechanism during decoding, effectively managing both monotonic and non-monotonic alignments. Meanwhile, transfer learning helps bridge the modality gap between vision and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09014","kind":"arxiv","version":4},"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/2412.09014/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":"2412.09014","created_at":"2026-07-05T09:53:46.790582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09014v4","created_at":"2026-07-05T09:53:46.790582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09014","created_at":"2026-07-05T09:53:46.790582+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZB6GSKYIBOJG","created_at":"2026-07-05T09:53:46.790582+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZB6GSKYIBOJG3GAJ","created_at":"2026-07-05T09:53:46.790582+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZB6GSKYI","created_at":"2026-07-05T09:53:46.790582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19352","citing_title":"Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards","ref_index":232,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4","json":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4.json","graph_json":"https://pith.science/api/pith-number/ZB6GSKYIBOJG3GAJEXKMFDQAD4/graph.json","events_json":"https://pith.science/api/pith-number/ZB6GSKYIBOJG3GAJEXKMFDQAD4/events.json","paper":"https://pith.science/paper/ZB6GSKYI"},"agent_actions":{"view_html":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4","download_json":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4.json","view_paper":"https://pith.science/paper/ZB6GSKYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09014&json=true","fetch_graph":"https://pith.science/api/pith-number/ZB6GSKYIBOJG3GAJEXKMFDQAD4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZB6GSKYIBOJG3GAJEXKMFDQAD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4/action/storage_attestation","attest_author":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4/action/author_attestation","sign_citation":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4/action/citation_signature","submit_replication":"https://pith.science/pith/ZB6GSKYIBOJG3GAJEXKMFDQAD4/action/replication_record"}},"created_at":"2026-07-05T09:53:46.790582+00:00","updated_at":"2026-07-05T09:53:46.790582+00:00"}