{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MDSIZTJPFN4ON7HW5HEUNDWHYZ","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":"ed8da009c68bc81978b8447384d9cd5979a4a4fe14306e1551e5801aaea3387f","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:34:34Z","title_canon_sha256":"7aa3dde4cb554c04e0b2c9377c3769a5a4d950348592f57f42a56143d900fb51"},"schema_version":"1.0","source":{"id":"2409.06666","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06666","created_at":"2026-07-05T10:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06666v2","created_at":"2026-07-05T10:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06666","created_at":"2026-07-05T10:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"MDSIZTJPFN4O","created_at":"2026-07-05T10:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"MDSIZTJPFN4ON7HW","created_at":"2026-07-05T10:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"MDSIZTJP","created_at":"2026-07-05T10:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:a3d3fe89198548864b348976f2863810675aca21a9da1705877e51454aee0638","target":"graph","created_at":"2026-07-05T10:22:04Z","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/2409.06666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interaction. However, there is still a lack of exploration on how to build speech interaction models based on open-source LLMs. To address this, we propose LLaMA-Omni, a novel model architecture designed for low-latency and high-quality speech interaction with LLMs. LLaMA-Omni integrates a pretrained speech encoder, a speech adaptor, an LLM, and a streaming speech decoder. It eliminates the need for speech transcription, an","authors_text":"Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Yan Zhou, Zhengrui Ma","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:34:34Z","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06666","kind":"arxiv","version":2},"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:d8976295bce7931812821cd5bccaa9d4a3f98d9c6e54ab5ea622b81dfbaae39a","target":"record","created_at":"2026-07-05T10:22:04Z","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":"ed8da009c68bc81978b8447384d9cd5979a4a4fe14306e1551e5801aaea3387f","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:34:34Z","title_canon_sha256":"7aa3dde4cb554c04e0b2c9377c3769a5a4d950348592f57f42a56143d900fb51"},"schema_version":"1.0","source":{"id":"2409.06666","kind":"arxiv","version":2}},"canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","first_computed_at":"2026-07-05T10:22:04.357619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:04.357619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"83y7PwsUb+ZFmOPOIaLltLRd167ZUujz3cRElr4uqvogBuz1gF0unmLCkhPyqsmo2Xkne0nevYbIYjYuhy+GDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:04.358204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06666","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8976295bce7931812821cd5bccaa9d4a3f98d9c6e54ab5ea622b81dfbaae39a","sha256:a3d3fe89198548864b348976f2863810675aca21a9da1705877e51454aee0638"],"state_sha256":"9896c1a0b5f863e985cfe57737c72247a5bebd29266af581464f51cd9853f038"}