{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PBSUR7KSFW4IAK2ALC2WORCSRR","short_pith_number":"pith:PBSUR7KS","schema_version":"1.0","canonical_sha256":"786548fd522db8802b4058b56744528c49682ecbb6f81d8dfd4bba957e3a5241","source":{"kind":"arxiv","id":"2409.11538","version":2},"attestation_state":"computed","paper":{"title":"Chain-of-Thought Prompting for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Chao-Han Huck Yang, Jagadeesh Balam, Ke Hu, Oleksii Hrinchuk, Piotr \\.Zelasko, Vitaly Lavrukhin, Zhehuai Chen","submitted_at":"2024-09-17T20:16:43Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable advancements in language understanding and generation. Building on the success of text-based LLMs, recent research has adapted these models to use speech embeddings for prompting, resulting in Speech-LLM models that exhibit strong performance in automatic speech recognition (ASR) and automatic speech translation (AST). In this work, we propose a novel approach to leverage ASR transcripts as prompts for AST in a Speech-LLM built on an encoder-decoder text LLM. The Speech-LLM model consists of a speech encoder and an encoder-decoder struc"},"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":"2409.11538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T20:16:43Z","cross_cats_sorted":[],"title_canon_sha256":"8f23232de9cc3a5e0efabb6d270d983c4b0ebc353f66762cf09d91a92116ba0f","abstract_canon_sha256":"dba5303ec4591fff12efdbebc2806e95540069843380201e6727d0830cbb21b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:46.244856Z","signature_b64":"703OIFpqcKwrgXP2j70AcAfEhjgBB0XJKimjATIICQdkS0l/jkZibzmewnhZ7i5VNk848Z9uYQyST/RALtbvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"786548fd522db8802b4058b56744528c49682ecbb6f81d8dfd4bba957e3a5241","last_reissued_at":"2026-07-05T10:39:46.244272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:46.244272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Thought Prompting for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Chao-Han Huck Yang, Jagadeesh Balam, Ke Hu, Oleksii Hrinchuk, Piotr \\.Zelasko, Vitaly Lavrukhin, Zhehuai Chen","submitted_at":"2024-09-17T20:16:43Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable advancements in language understanding and generation. Building on the success of text-based LLMs, recent research has adapted these models to use speech embeddings for prompting, resulting in Speech-LLM models that exhibit strong performance in automatic speech recognition (ASR) and automatic speech translation (AST). In this work, we propose a novel approach to leverage ASR transcripts as prompts for AST in a Speech-LLM built on an encoder-decoder text LLM. The Speech-LLM model consists of a speech encoder and an encoder-decoder struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11538","kind":"arxiv","version":2},"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/2409.11538/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":"2409.11538","created_at":"2026-07-05T10:39:46.244346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11538v2","created_at":"2026-07-05T10:39:46.244346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11538","created_at":"2026-07-05T10:39:46.244346+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBSUR7KSFW4I","created_at":"2026-07-05T10:39:46.244346+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBSUR7KSFW4IAK2A","created_at":"2026-07-05T10:39:46.244346+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBSUR7KS","created_at":"2026-07-05T10:39:46.244346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.08528","citing_title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08363","citing_title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR","json":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR.json","graph_json":"https://pith.science/api/pith-number/PBSUR7KSFW4IAK2ALC2WORCSRR/graph.json","events_json":"https://pith.science/api/pith-number/PBSUR7KSFW4IAK2ALC2WORCSRR/events.json","paper":"https://pith.science/paper/PBSUR7KS"},"agent_actions":{"view_html":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR","download_json":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR.json","view_paper":"https://pith.science/paper/PBSUR7KS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11538&json=true","fetch_graph":"https://pith.science/api/pith-number/PBSUR7KSFW4IAK2ALC2WORCSRR/graph.json","fetch_events":"https://pith.science/api/pith-number/PBSUR7KSFW4IAK2ALC2WORCSRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR/action/storage_attestation","attest_author":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR/action/author_attestation","sign_citation":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR/action/citation_signature","submit_replication":"https://pith.science/pith/PBSUR7KSFW4IAK2ALC2WORCSRR/action/replication_record"}},"created_at":"2026-07-05T10:39:46.244346+00:00","updated_at":"2026-07-05T10:39:46.244346+00:00"}