{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:45WI3DSXUIOHYAUWMFM7VUN2CH","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":"0f7a4329d6a1ac9f92ef4e5b69d40e5a97581a72c694922abfefca42ced0f1e9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T14:42:49Z","title_canon_sha256":"d343e478a3cee42084b43e6cff5dbca6874d9f382ecb6f5aa719480834f63d2f"},"schema_version":"1.0","source":{"id":"2407.03169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03169","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03169v1","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03169","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"45WI3DSXUIOH","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"45WI3DSXUIOHYAUW","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"45WI3DSX","created_at":"2026-07-05T08:39:47Z"}],"graph_snapshots":[{"event_id":"sha256:5af4c5fd8271f610ee6952fc95dfc37c2f138e880beb0301b4950ba3bfacdac5","target":"graph","created_at":"2026-07-05T08:39:47Z","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/2407.03169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao-Wei Huang, Hirofumi Inaguma, Hongyu Gong, Hui Lu, Ilia Kulikov, Ruslan Mavlyutov, Sravya Popuri","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T14:42:49Z","title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03169","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":"sha256:4cf40c5e1196c439d6c41f611d296e7564863bb9725ca1b7d7a2ac40ad3d0335","target":"record","created_at":"2026-07-05T08:39:47Z","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":"0f7a4329d6a1ac9f92ef4e5b69d40e5a97581a72c694922abfefca42ced0f1e9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T14:42:49Z","title_canon_sha256":"d343e478a3cee42084b43e6cff5dbca6874d9f382ecb6f5aa719480834f63d2f"},"schema_version":"1.0","source":{"id":"2407.03169","kind":"arxiv","version":1}},"canonical_sha256":"e76c8d8e57a21c7c02966159fad1ba11e09b53d2a222be85705602706eb27604","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e76c8d8e57a21c7c02966159fad1ba11e09b53d2a222be85705602706eb27604","first_computed_at":"2026-07-05T08:39:47.267147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:47.267147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDKktS2/RT3iH3kla+iYeQviFYmi1QsjJCTQdXAsA1oLj17izBAKjT0vfv89tBpBomnlfdTMm3rA6wd7ofmjAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:47.267659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cf40c5e1196c439d6c41f611d296e7564863bb9725ca1b7d7a2ac40ad3d0335","sha256:5af4c5fd8271f610ee6952fc95dfc37c2f138e880beb0301b4950ba3bfacdac5"],"state_sha256":"423c6c9f650dc68a03eecaf952ccda22b8442f4485a078965f759b9ed571b078"}