{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QXFA426CSRJK6DQOHHZSXPQIXW","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":"cf4c88825fa817137d9fadcb8976dc65298327ac0e6794a687e08907ce60124b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:28:13Z","title_canon_sha256":"ccb92ae8d756fd0faa2b0aa753ed6114f2bdf181d79b80d2711aae1d29ac3f75"},"schema_version":"1.0","source":{"id":"2406.09345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09345","created_at":"2026-07-05T08:31:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09345v1","created_at":"2026-07-05T08:31:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09345","created_at":"2026-07-05T08:31:31Z"},{"alias_kind":"pith_short_12","alias_value":"QXFA426CSRJK","created_at":"2026-07-05T08:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"QXFA426CSRJK6DQO","created_at":"2026-07-05T08:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"QXFA426C","created_at":"2026-07-05T08:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:eb3ab17b3c337da8f3c28bebcbcfb500f4de36a2c3787172f850d140964eccc3","target":"graph","created_at":"2026-07-05T08:31:31Z","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/2406.09345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an LLM, trained on diverse tasks. We propose the use of discrete speech units (DSU), rather than continuous-valued speech encoder outputs, that are converted to the LLM token embedding space using the speech adapter. We generate DSU using a self-supervised speech encoder followed by k-means clustering. The proposed model shows robust performance on speech inpu","authors_text":"Karen Livescu, Kwangyoun Kim, Prashant Sridhar, Shinji Watanabe, Suwon Shon, Yi-Te Hsu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:28:13Z","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09345","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:c9654c7cfe336cc326e0ae9970b54ce399c44634adceb52d76f90eddd3bdab7a","target":"record","created_at":"2026-07-05T08:31:31Z","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":"cf4c88825fa817137d9fadcb8976dc65298327ac0e6794a687e08907ce60124b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:28:13Z","title_canon_sha256":"ccb92ae8d756fd0faa2b0aa753ed6114f2bdf181d79b80d2711aae1d29ac3f75"},"schema_version":"1.0","source":{"id":"2406.09345","kind":"arxiv","version":1}},"canonical_sha256":"85ca0e6bc29452af0e0e39f32bbe08bda2ba5cc23df1684f964f5c6d11f1eb1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85ca0e6bc29452af0e0e39f32bbe08bda2ba5cc23df1684f964f5c6d11f1eb1c","first_computed_at":"2026-07-05T08:31:31.614970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:31.614970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHdyrQYvm3EMBebX0SC244zw38wHRsVBjA+Q6/uUbSgGi93AdMSwBVxi0JS+5xLvDdOsW08fWtsB52ZbGOlyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:31.615468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9654c7cfe336cc326e0ae9970b54ce399c44634adceb52d76f90eddd3bdab7a","sha256:eb3ab17b3c337da8f3c28bebcbcfb500f4de36a2c3787172f850d140964eccc3"],"state_sha256":"62e2c3ec251588843842d07c08cd4e726b3c85906900abce3058f9b9ae754ddb"}