{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EZEZ5JW24FEAOTVTOGNSYJ6OZS","short_pith_number":"pith:EZEZ5JW2","schema_version":"1.0","canonical_sha256":"26499ea6dae148074eb3719b2c27ceccbfbdf2c35604df0c234a100f76010a62","source":{"kind":"arxiv","id":"2412.18495","version":1},"attestation_state":"computed","paper":{"title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dominik Mach\\'a\\v{c}ek, Ond\\v{r}ej Bojar, Peter Polak, Sara Papi","submitted_at":"2024-12-24T15:26:31Z","abstract_excerpt":"Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker's speech, ensuring low latency for better user comprehension. Despite its intended application to unbounded speech, most research has focused on human pre-segmented speech, simplifying the task and overlooking significant challenges. This narrow focus, coupled with widespread terminological inconsistencies, is limiting the applicability of research outcomes to real-world applications, ultimately hindering progress in the field. Our extensive literature rev"},"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":"2412.18495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T15:26:31Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"7ddba052203b3e7d85c7c09c6bd2fb4702c81c2b52e8a88b436b9888cf1a7d5a","abstract_canon_sha256":"752d9ee59cfce2a62556c71644a43fbe6c0a43b357161d8bdf016f936fa18195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:56.640091Z","signature_b64":"PkNnEnjkN1JlP2k7M7lSY3drl9KI2zP+Nhm3Be7+5mSxkwYb08KT2fVLeWs+Fgrnj2W7AiE6nsz9tJJwiCoJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26499ea6dae148074eb3719b2c27ceccbfbdf2c35604df0c234a100f76010a62","last_reissued_at":"2026-07-05T09:53:56.639664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:56.639664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dominik Mach\\'a\\v{c}ek, Ond\\v{r}ej Bojar, Peter Polak, Sara Papi","submitted_at":"2024-12-24T15:26:31Z","abstract_excerpt":"Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker's speech, ensuring low latency for better user comprehension. Despite its intended application to unbounded speech, most research has focused on human pre-segmented speech, simplifying the task and overlooking significant challenges. This narrow focus, coupled with widespread terminological inconsistencies, is limiting the applicability of research outcomes to real-world applications, ultimately hindering progress in the field. Our extensive literature rev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18495","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/2412.18495/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":"2412.18495","created_at":"2026-07-05T09:53:56.639731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18495v1","created_at":"2026-07-05T09:53:56.639731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18495","created_at":"2026-07-05T09:53:56.639731+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZEZ5JW24FEA","created_at":"2026-07-05T09:53:56.639731+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZEZ5JW24FEAOTVT","created_at":"2026-07-05T09:53:56.639731+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZEZ5JW2","created_at":"2026-07-05T09:53:56.639731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02683","citing_title":"Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS","json":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS.json","graph_json":"https://pith.science/api/pith-number/EZEZ5JW24FEAOTVTOGNSYJ6OZS/graph.json","events_json":"https://pith.science/api/pith-number/EZEZ5JW24FEAOTVTOGNSYJ6OZS/events.json","paper":"https://pith.science/paper/EZEZ5JW2"},"agent_actions":{"view_html":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS","download_json":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS.json","view_paper":"https://pith.science/paper/EZEZ5JW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18495&json=true","fetch_graph":"https://pith.science/api/pith-number/EZEZ5JW24FEAOTVTOGNSYJ6OZS/graph.json","fetch_events":"https://pith.science/api/pith-number/EZEZ5JW24FEAOTVTOGNSYJ6OZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS/action/storage_attestation","attest_author":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS/action/author_attestation","sign_citation":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS/action/citation_signature","submit_replication":"https://pith.science/pith/EZEZ5JW24FEAOTVTOGNSYJ6OZS/action/replication_record"}},"created_at":"2026-07-05T09:53:56.639731+00:00","updated_at":"2026-07-05T09:53:56.639731+00:00"}