{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5PB7OEA2XNLEP6BEBKSFXOYQWD","short_pith_number":"pith:5PB7OEA2","schema_version":"1.0","canonical_sha256":"ebc3f7101abb5647f8240aa45bbb10b0f3fc339ca0d8ee538d992a908448dc62","source":{"kind":"arxiv","id":"2004.12111","version":1},"attestation_state":"computed","paper":{"title":"Jointly Trained Transformers models for Spoken Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hari Krishna Vydana, Honza Cernocky, Katerina Zmolikova, Luk'as Burget, Martin Karafi'at","submitted_at":"2020-04-25T11:28:39Z","abstract_excerpt":"Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to translate source text to text in target language. Recent progress in the sequence-sequence architectures have reduced the performance gap between the pipeline based SLT systems (cascaded ASR-MT) and End-to-End approaches. Though End-to-End and cascaded ASR-MT systems are reaching to the comparable levels of performances, we can see a large performance gap usin"},"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":"2004.12111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-04-25T11:28:39Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"9758b4c61484bae3957e594be6972d44866178fc8ac55565d91deeb6254fb548","abstract_canon_sha256":"1452479c00575e8ca310ea73444e8c336a1224140b390f7d4d9dadc6779830d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:12.384283Z","signature_b64":"B1Dwo3S2hnx6J+un6tw9FkV3JJQqnLfrvl8k/pZkF3Iyg/be/tSAAzQWfegB9wy/8qLbf7T/OdcvgfTWkP+2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc3f7101abb5647f8240aa45bbb10b0f3fc339ca0d8ee538d992a908448dc62","last_reissued_at":"2026-07-05T00:58:12.383794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:12.383794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jointly Trained Transformers models for Spoken Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hari Krishna Vydana, Honza Cernocky, Katerina Zmolikova, Luk'as Burget, Martin Karafi'at","submitted_at":"2020-04-25T11:28:39Z","abstract_excerpt":"Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to translate source text to text in target language. Recent progress in the sequence-sequence architectures have reduced the performance gap between the pipeline based SLT systems (cascaded ASR-MT) and End-to-End approaches. Though End-to-End and cascaded ASR-MT systems are reaching to the comparable levels of performances, we can see a large performance gap usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12111","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/2004.12111/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":"2004.12111","created_at":"2026-07-05T00:58:12.383855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12111v1","created_at":"2026-07-05T00:58:12.383855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12111","created_at":"2026-07-05T00:58:12.383855+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PB7OEA2XNLE","created_at":"2026-07-05T00:58:12.383855+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PB7OEA2XNLEP6BE","created_at":"2026-07-05T00:58:12.383855+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PB7OEA2","created_at":"2026-07-05T00:58:12.383855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD","json":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD.json","graph_json":"https://pith.science/api/pith-number/5PB7OEA2XNLEP6BEBKSFXOYQWD/graph.json","events_json":"https://pith.science/api/pith-number/5PB7OEA2XNLEP6BEBKSFXOYQWD/events.json","paper":"https://pith.science/paper/5PB7OEA2"},"agent_actions":{"view_html":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD","download_json":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD.json","view_paper":"https://pith.science/paper/5PB7OEA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12111&json=true","fetch_graph":"https://pith.science/api/pith-number/5PB7OEA2XNLEP6BEBKSFXOYQWD/graph.json","fetch_events":"https://pith.science/api/pith-number/5PB7OEA2XNLEP6BEBKSFXOYQWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD/action/storage_attestation","attest_author":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD/action/author_attestation","sign_citation":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD/action/citation_signature","submit_replication":"https://pith.science/pith/5PB7OEA2XNLEP6BEBKSFXOYQWD/action/replication_record"}},"created_at":"2026-07-05T00:58:12.383855+00:00","updated_at":"2026-07-05T00:58:12.383855+00:00"}