{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2GRLTN2YVY2SCPNJXGBITNWNOB","short_pith_number":"pith:2GRLTN2Y","schema_version":"1.0","canonical_sha256":"d1a2b9b758ae35213da9b98289b6cd7078b4471e3af626df3f4918c1611b2c85","source":{"kind":"arxiv","id":"2407.11010","version":1},"attestation_state":"computed","paper":{"title":"Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Frank Seide, Rastislav Rabatin","submitted_at":"2024-06-26T07:34:53Z","abstract_excerpt":"We adapt the well-known beam-search algorithm for machine translation to operate in a cascaded real-time speech translation system. This proved to be more complex than initially anticipated, due to four key challenges: (1) real-time processing of intermediate and final transcriptions with incomplete words from ASR, (2) emitting intermediate and final translations with minimal user perceived latency, (3) handling beam search hypotheses that have unequal length and different model state, and (4) handling sentence boundaries. Previous work in the field of simultaneous machine translation only imp"},"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":"2407.11010","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T07:34:53Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"1d4090124255c10580c856346dfd12ff446d895328e423ca245611aa54933b56","abstract_canon_sha256":"6c09f09b5e4f6a79257b2f22e362e3bfe4bdbdd1a1777382edaf43f87757a639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:17.019124Z","signature_b64":"sN8102pG/5raHlF+ZTa+OeiCCsX5JrwwpjZszrVNoe9sDm0a0wy6oscv6mQSIauGjflcO33/sW2c7N+pCUHbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1a2b9b758ae35213da9b98289b6cd7078b4471e3af626df3f4918c1611b2c85","last_reissued_at":"2026-07-05T08:44:17.018589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:17.018589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Frank Seide, Rastislav Rabatin","submitted_at":"2024-06-26T07:34:53Z","abstract_excerpt":"We adapt the well-known beam-search algorithm for machine translation to operate in a cascaded real-time speech translation system. This proved to be more complex than initially anticipated, due to four key challenges: (1) real-time processing of intermediate and final transcriptions with incomplete words from ASR, (2) emitting intermediate and final translations with minimal user perceived latency, (3) handling beam search hypotheses that have unequal length and different model state, and (4) handling sentence boundaries. Previous work in the field of simultaneous machine translation only imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11010","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/2407.11010/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":"2407.11010","created_at":"2026-07-05T08:44:17.018650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11010v1","created_at":"2026-07-05T08:44:17.018650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11010","created_at":"2026-07-05T08:44:17.018650+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GRLTN2YVY2S","created_at":"2026-07-05T08:44:17.018650+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GRLTN2YVY2SCPNJ","created_at":"2026-07-05T08:44:17.018650+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GRLTN2Y","created_at":"2026-07-05T08:44:17.018650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02157","citing_title":"HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB","json":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB.json","graph_json":"https://pith.science/api/pith-number/2GRLTN2YVY2SCPNJXGBITNWNOB/graph.json","events_json":"https://pith.science/api/pith-number/2GRLTN2YVY2SCPNJXGBITNWNOB/events.json","paper":"https://pith.science/paper/2GRLTN2Y"},"agent_actions":{"view_html":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB","download_json":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB.json","view_paper":"https://pith.science/paper/2GRLTN2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11010&json=true","fetch_graph":"https://pith.science/api/pith-number/2GRLTN2YVY2SCPNJXGBITNWNOB/graph.json","fetch_events":"https://pith.science/api/pith-number/2GRLTN2YVY2SCPNJXGBITNWNOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB/action/storage_attestation","attest_author":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB/action/author_attestation","sign_citation":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB/action/citation_signature","submit_replication":"https://pith.science/pith/2GRLTN2YVY2SCPNJXGBITNWNOB/action/replication_record"}},"created_at":"2026-07-05T08:44:17.018650+00:00","updated_at":"2026-07-05T08:44:17.018650+00:00"}