{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DXWYRYERLEGPAUYC66SZDCD5IJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9a461c98d38aaa0d70a66a7418f5797b39fe59f43847166d60ee20bb1b661b00","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T05:32:49Z","title_canon_sha256":"d16296ebe425a8da04b7a5c558ef9d2bb7b2ec0a6793f97e8d6d5d9b8f961602"},"schema_version":"1.0","source":{"id":"2312.13585","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13585","created_at":"2026-07-05T07:26:47Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13585v1","created_at":"2026-07-05T07:26:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13585","created_at":"2026-07-05T07:26:47Z"},{"alias_kind":"pith_short_12","alias_value":"DXWYRYERLEGP","created_at":"2026-07-05T07:26:47Z"},{"alias_kind":"pith_short_16","alias_value":"DXWYRYERLEGPAUYC","created_at":"2026-07-05T07:26:47Z"},{"alias_kind":"pith_short_8","alias_value":"DXWYRYER","created_at":"2026-07-05T07:26:47Z"}],"graph_snapshots":[{"event_id":"sha256:f784a8cacb71d1b4cb3744072f1a3ba6f5d36c75df9da28f6d7055a5ad3d8e3c","target":"graph","created_at":"2026-07-05T07:26:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.13585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the great success of large language models (LLMs) across various tasks, in this paper, we introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained LLM. By integrating the large language model (LLM) with a speech encoder and employing multi-task instruction tuning, LLM-ST can produce accurate timestamped transcriptions and translations, even from long audio inputs. Furthermore, our findings indicate that the implementation of Chain-of-Thought (CoT) prompting can yield advantages in the context of LLM-ST. Through rigorous experimentation on English an","authors_text":"Hang Li, Mingxuan Wang, Qianqian Dong, Rong Ye, Shanbo Cheng, Tom Ko, Zhichao Huang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T05:32:49Z","title":"Speech Translation with Large Language Models: An Industrial Practice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13585","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:161f8d2ff378c7f9cd5516a5ca7b614fb5900c63ee9a860fbf6d360ce9303cc8","target":"record","created_at":"2026-07-05T07:26:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9a461c98d38aaa0d70a66a7418f5797b39fe59f43847166d60ee20bb1b661b00","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T05:32:49Z","title_canon_sha256":"d16296ebe425a8da04b7a5c558ef9d2bb7b2ec0a6793f97e8d6d5d9b8f961602"},"schema_version":"1.0","source":{"id":"2312.13585","kind":"arxiv","version":1}},"canonical_sha256":"1ded88e091590cf05302f7a591887d4273f7a54b19d8712f484f2b7075d49f1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ded88e091590cf05302f7a591887d4273f7a54b19d8712f484f2b7075d49f1e","first_computed_at":"2026-07-05T07:26:47.098674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:47.098674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W41TGvSIjR7zDaG4nUv9ujFLrHl+RLM4PXwnEvTyukz5kQbvMWc6mssP7ZgrBxXKi7SYtfZ1HBf9d2Z0lx6ZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:47.099183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13585","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:161f8d2ff378c7f9cd5516a5ca7b614fb5900c63ee9a860fbf6d360ce9303cc8","sha256:f784a8cacb71d1b4cb3744072f1a3ba6f5d36c75df9da28f6d7055a5ad3d8e3c"],"state_sha256":"c36abb8d0b7c5e85594fcb2462a1293697d05cb8518b1ac65018ddc42fe8a02b"}