{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3U2B7VQE7GJY4UOFCK5AQFT5VC","short_pith_number":"pith:3U2B7VQE","schema_version":"1.0","canonical_sha256":"dd341fd604f9938e51c512ba08167da8b434096a74f60ebbd5cd3e04c9297af7","source":{"kind":"arxiv","id":"2210.09754","version":1},"attestation_state":"computed","paper":{"title":"Simultaneous Translation for Unsegmented Input: A Sliding Window Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barry Haddow, Ond\\v{r}ej Bojar, Sukanta Sen","submitted_at":"2022-10-18T11:07:28Z","abstract_excerpt":"In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous segmentation, due to poor sentence-final punctuation by the ASR system, leads to degradation in translation quality, especially in the simultaneous (online) setting where the input is continuously updated. To reduce the influence of automatic segmentation, we present a sliding window approach to translate raw ASR outputs (online or offline) without needing to rely o"},"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":"2210.09754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-18T11:07:28Z","cross_cats_sorted":[],"title_canon_sha256":"fdeb191225644fe9369668265e9deae1ab5486036abf3687cc7fe507ed5fe2a7","abstract_canon_sha256":"069dd66f982c5578ac33fd2c260246b855e853cdc84abcdaf4b259cc2cc011b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:59.162329Z","signature_b64":"PR7z7azbY04c5EsNkHxwZOFNoPeq4J/gC6XpnLGkMLWnFbk3lxZcRhUBPWR45WN0sQ5AheCQb4CyKlbpOVVSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd341fd604f9938e51c512ba08167da8b434096a74f60ebbd5cd3e04c9297af7","last_reissued_at":"2026-07-05T05:07:59.161986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:59.161986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simultaneous Translation for Unsegmented Input: A Sliding Window Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barry Haddow, Ond\\v{r}ej Bojar, Sukanta Sen","submitted_at":"2022-10-18T11:07:28Z","abstract_excerpt":"In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous segmentation, due to poor sentence-final punctuation by the ASR system, leads to degradation in translation quality, especially in the simultaneous (online) setting where the input is continuously updated. To reduce the influence of automatic segmentation, we present a sliding window approach to translate raw ASR outputs (online or offline) without needing to rely o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09754","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/2210.09754/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":"2210.09754","created_at":"2026-07-05T05:07:59.162036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09754v1","created_at":"2026-07-05T05:07:59.162036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09754","created_at":"2026-07-05T05:07:59.162036+00:00"},{"alias_kind":"pith_short_12","alias_value":"3U2B7VQE7GJY","created_at":"2026-07-05T05:07:59.162036+00:00"},{"alias_kind":"pith_short_16","alias_value":"3U2B7VQE7GJY4UOF","created_at":"2026-07-05T05:07:59.162036+00:00"},{"alias_kind":"pith_short_8","alias_value":"3U2B7VQE","created_at":"2026-07-05T05:07:59.162036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03948","citing_title":"A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC","json":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC.json","graph_json":"https://pith.science/api/pith-number/3U2B7VQE7GJY4UOFCK5AQFT5VC/graph.json","events_json":"https://pith.science/api/pith-number/3U2B7VQE7GJY4UOFCK5AQFT5VC/events.json","paper":"https://pith.science/paper/3U2B7VQE"},"agent_actions":{"view_html":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC","download_json":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC.json","view_paper":"https://pith.science/paper/3U2B7VQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09754&json=true","fetch_graph":"https://pith.science/api/pith-number/3U2B7VQE7GJY4UOFCK5AQFT5VC/graph.json","fetch_events":"https://pith.science/api/pith-number/3U2B7VQE7GJY4UOFCK5AQFT5VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC/action/storage_attestation","attest_author":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC/action/author_attestation","sign_citation":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC/action/citation_signature","submit_replication":"https://pith.science/pith/3U2B7VQE7GJY4UOFCK5AQFT5VC/action/replication_record"}},"created_at":"2026-07-05T05:07:59.162036+00:00","updated_at":"2026-07-05T05:07:59.162036+00:00"}