{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:45WI3DSXUIOHYAUWMFM7VUN2CH","short_pith_number":"pith:45WI3DSX","schema_version":"1.0","canonical_sha256":"e76c8d8e57a21c7c02966159fad1ba11e09b53d2a222be85705602706eb27604","source":{"kind":"arxiv","id":"2407.03169","version":1},"attestation_state":"computed","paper":{"title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Wei Huang, Hirofumi Inaguma, Hongyu Gong, Hui Lu, Ilia Kulikov, Ruslan Mavlyutov, Sravya Popuri","submitted_at":"2024-07-03T14:42:49Z","abstract_excerpt":"Large language models (LLMs), known for their exceptional reasoning capabilities, generalizability, and fluency across diverse domains, present a promising avenue for enhancing speech-related tasks. In this paper, we focus on integrating decoder-only LLMs to the task of speech-to-text translation (S2TT). We propose a decoder-only architecture that enables the LLM to directly consume the encoded speech representation and generate the text translation. Additionally, we investigate the effects of different parameter-efficient fine-tuning techniques and task formulation. Our model achieves state-o"},"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":"2407.03169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T14:42:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d343e478a3cee42084b43e6cff5dbca6874d9f382ecb6f5aa719480834f63d2f","abstract_canon_sha256":"0f7a4329d6a1ac9f92ef4e5b69d40e5a97581a72c694922abfefca42ced0f1e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:47.267659Z","signature_b64":"TDKktS2/RT3iH3kla+iYeQviFYmi1QsjJCTQdXAsA1oLj17izBAKjT0vfv89tBpBomnlfdTMm3rA6wd7ofmjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e76c8d8e57a21c7c02966159fad1ba11e09b53d2a222be85705602706eb27604","last_reissued_at":"2026-07-05T08:39:47.267147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:47.267147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Wei Huang, Hirofumi Inaguma, Hongyu Gong, Hui Lu, Ilia Kulikov, Ruslan Mavlyutov, Sravya Popuri","submitted_at":"2024-07-03T14:42:49Z","abstract_excerpt":"Large language models (LLMs), known for their exceptional reasoning capabilities, generalizability, and fluency across diverse domains, present a promising avenue for enhancing speech-related tasks. In this paper, we focus on integrating decoder-only LLMs to the task of speech-to-text translation (S2TT). We propose a decoder-only architecture that enables the LLM to directly consume the encoded speech representation and generate the text translation. Additionally, we investigate the effects of different parameter-efficient fine-tuning techniques and task formulation. Our model achieves state-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03169","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/2407.03169/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":"2407.03169","created_at":"2026-07-05T08:39:47.267208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03169v1","created_at":"2026-07-05T08:39:47.267208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03169","created_at":"2026-07-05T08:39:47.267208+00:00"},{"alias_kind":"pith_short_12","alias_value":"45WI3DSXUIOH","created_at":"2026-07-05T08:39:47.267208+00:00"},{"alias_kind":"pith_short_16","alias_value":"45WI3DSXUIOHYAUW","created_at":"2026-07-05T08:39:47.267208+00:00"},{"alias_kind":"pith_short_8","alias_value":"45WI3DSX","created_at":"2026-07-05T08:39:47.267208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02370","citing_title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH","json":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH.json","graph_json":"https://pith.science/api/pith-number/45WI3DSXUIOHYAUWMFM7VUN2CH/graph.json","events_json":"https://pith.science/api/pith-number/45WI3DSXUIOHYAUWMFM7VUN2CH/events.json","paper":"https://pith.science/paper/45WI3DSX"},"agent_actions":{"view_html":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH","download_json":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH.json","view_paper":"https://pith.science/paper/45WI3DSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03169&json=true","fetch_graph":"https://pith.science/api/pith-number/45WI3DSXUIOHYAUWMFM7VUN2CH/graph.json","fetch_events":"https://pith.science/api/pith-number/45WI3DSXUIOHYAUWMFM7VUN2CH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH/action/storage_attestation","attest_author":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH/action/author_attestation","sign_citation":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH/action/citation_signature","submit_replication":"https://pith.science/pith/45WI3DSXUIOHYAUWMFM7VUN2CH/action/replication_record"}},"created_at":"2026-07-05T08:39:47.267208+00:00","updated_at":"2026-07-05T08:39:47.267208+00:00"}