{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HSCKRXBLFLP6PNPXCU762B3ZFG","short_pith_number":"pith:HSCKRXBL","schema_version":"1.0","canonical_sha256":"3c84a8dc2b2adfe7b5f7153fed0779298af38879820e6d1685ac887abc7fbdc1","source":{"kind":"arxiv","id":"2310.02050","version":1},"attestation_state":"computed","paper":{"title":"Tuning Large language model for End-to-end Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dan Qu, Hao Zhang, Nianwen Si, Wenlin Zhang, Xiaolin Jiao, Xukui Yang, Yaqi Chen","submitted_at":"2023-10-03T13:43:50Z","abstract_excerpt":"With the emergence of large language models (LLMs), multimodal models based on LLMs have demonstrated significant potential. Models such as LLaSM, X-LLM, and SpeechGPT exhibit an impressive ability to comprehend and generate human instructions. However, their performance often falters when faced with complex tasks like end-to-end speech translation (E2E-ST), a cross-language and cross-modal translation task. In comparison to single-modal models, multimodal models lag behind in these scenarios. This paper introduces LST, a Large multimodal model designed to excel at the E2E-ST task. LST consist"},"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":"2310.02050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T13:43:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d38ce09eaf15914b3f36dbb9891baedb90ffd48eb4b58aac902e219aa1e5a7a1","abstract_canon_sha256":"ba4b010b5baf5794736e61d7427e44d14cae359f38cff45bf227b6e75787ef9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:49.376875Z","signature_b64":"9FzdgsWuzlAgefsAIoEnITxRFIYUQHEFJ7tdOV8Vi1+HeNN51WBlEtmid1Svu5DB0AtaldIvX4eeCfNdMIWvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c84a8dc2b2adfe7b5f7153fed0779298af38879820e6d1685ac887abc7fbdc1","last_reissued_at":"2026-07-05T06:56:49.376371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:49.376371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuning Large language model for End-to-end Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dan Qu, Hao Zhang, Nianwen Si, Wenlin Zhang, Xiaolin Jiao, Xukui Yang, Yaqi Chen","submitted_at":"2023-10-03T13:43:50Z","abstract_excerpt":"With the emergence of large language models (LLMs), multimodal models based on LLMs have demonstrated significant potential. Models such as LLaSM, X-LLM, and SpeechGPT exhibit an impressive ability to comprehend and generate human instructions. However, their performance often falters when faced with complex tasks like end-to-end speech translation (E2E-ST), a cross-language and cross-modal translation task. In comparison to single-modal models, multimodal models lag behind in these scenarios. This paper introduces LST, a Large multimodal model designed to excel at the E2E-ST task. LST consist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02050","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/2310.02050/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":"2310.02050","created_at":"2026-07-05T06:56:49.376441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02050v1","created_at":"2026-07-05T06:56:49.376441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02050","created_at":"2026-07-05T06:56:49.376441+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSCKRXBLFLP6","created_at":"2026-07-05T06:56:49.376441+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSCKRXBLFLP6PNPX","created_at":"2026-07-05T06:56:49.376441+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSCKRXBL","created_at":"2026-07-05T06:56:49.376441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21453","citing_title":"CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG","json":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG.json","graph_json":"https://pith.science/api/pith-number/HSCKRXBLFLP6PNPXCU762B3ZFG/graph.json","events_json":"https://pith.science/api/pith-number/HSCKRXBLFLP6PNPXCU762B3ZFG/events.json","paper":"https://pith.science/paper/HSCKRXBL"},"agent_actions":{"view_html":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG","download_json":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG.json","view_paper":"https://pith.science/paper/HSCKRXBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02050&json=true","fetch_graph":"https://pith.science/api/pith-number/HSCKRXBLFLP6PNPXCU762B3ZFG/graph.json","fetch_events":"https://pith.science/api/pith-number/HSCKRXBLFLP6PNPXCU762B3ZFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG/action/storage_attestation","attest_author":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG/action/author_attestation","sign_citation":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG/action/citation_signature","submit_replication":"https://pith.science/pith/HSCKRXBLFLP6PNPXCU762B3ZFG/action/replication_record"}},"created_at":"2026-07-05T06:56:49.376441+00:00","updated_at":"2026-07-05T06:56:49.376441+00:00"}