{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OZQQANDMBHENUBX5R2T37ENVTT","short_pith_number":"pith:OZQQANDM","schema_version":"1.0","canonical_sha256":"766100346c09c8da06fd8ea7bf91b59cedb34400da6c0010cdac5069bddfd121","source":{"kind":"arxiv","id":"2506.13143","version":1},"attestation_state":"computed","paper":{"title":"CMU's IWSLT 2025 Simultaneous Speech Translation System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lei Li, Siqi Ouyang, Xi Xu","submitted_at":"2025-06-16T06:56:21Z","abstract_excerpt":"This paper presents CMU's submission to the IWSLT 2025 Simultaneous Speech Translation (SST) task for translating unsegmented English speech into Chinese and German text in a streaming manner. Our end-to-end speech-to-text system integrates a chunkwise causal Wav2Vec 2.0 speech encoder, an adapter, and the Qwen2.5-7B-Instruct as the decoder. We use a two-stage simultaneous training procedure on robust speech segments curated from LibriSpeech, CommonVoice, and VoxPopuli datasets, utilizing standard cross-entropy loss. Our model supports adjustable latency through a configurable latency multipli"},"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":"2506.13143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T06:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"40279ba30abe60e53e6ec6f1a628732c8c9e00188f0ae1b3979d3f8a80c915e3","abstract_canon_sha256":"6c94239e1f623d28fdefcd965cbfc6ac9e813ae971da712613c9c798460017ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:05.851832Z","signature_b64":"Lj9qRiO2W9Bexm6tRO0n8meo3AuG6kFZyKkyyhwNEhtZhhEJwFg8tZ4e22ABxd3UuS+MssOGh1g55pCOJ2BHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"766100346c09c8da06fd8ea7bf91b59cedb34400da6c0010cdac5069bddfd121","last_reissued_at":"2026-07-05T11:22:05.851354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:05.851354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMU's IWSLT 2025 Simultaneous Speech Translation System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lei Li, Siqi Ouyang, Xi Xu","submitted_at":"2025-06-16T06:56:21Z","abstract_excerpt":"This paper presents CMU's submission to the IWSLT 2025 Simultaneous Speech Translation (SST) task for translating unsegmented English speech into Chinese and German text in a streaming manner. Our end-to-end speech-to-text system integrates a chunkwise causal Wav2Vec 2.0 speech encoder, an adapter, and the Qwen2.5-7B-Instruct as the decoder. We use a two-stage simultaneous training procedure on robust speech segments curated from LibriSpeech, CommonVoice, and VoxPopuli datasets, utilizing standard cross-entropy loss. Our model supports adjustable latency through a configurable latency multipli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13143","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/2506.13143/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":"2506.13143","created_at":"2026-07-05T11:22:05.851414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13143v1","created_at":"2026-07-05T11:22:05.851414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13143","created_at":"2026-07-05T11:22:05.851414+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZQQANDMBHEN","created_at":"2026-07-05T11:22:05.851414+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZQQANDMBHENUBX5","created_at":"2026-07-05T11:22:05.851414+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZQQANDM","created_at":"2026-07-05T11:22:05.851414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17527","citing_title":"Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT","json":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT.json","graph_json":"https://pith.science/api/pith-number/OZQQANDMBHENUBX5R2T37ENVTT/graph.json","events_json":"https://pith.science/api/pith-number/OZQQANDMBHENUBX5R2T37ENVTT/events.json","paper":"https://pith.science/paper/OZQQANDM"},"agent_actions":{"view_html":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT","download_json":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT.json","view_paper":"https://pith.science/paper/OZQQANDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13143&json=true","fetch_graph":"https://pith.science/api/pith-number/OZQQANDMBHENUBX5R2T37ENVTT/graph.json","fetch_events":"https://pith.science/api/pith-number/OZQQANDMBHENUBX5R2T37ENVTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT/action/storage_attestation","attest_author":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT/action/author_attestation","sign_citation":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT/action/citation_signature","submit_replication":"https://pith.science/pith/OZQQANDMBHENUBX5R2T37ENVTT/action/replication_record"}},"created_at":"2026-07-05T11:22:05.851414+00:00","updated_at":"2026-07-05T11:22:05.851414+00:00"}