{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MDSIZTJPFN4ON7HW5HEUNDWHYZ","short_pith_number":"pith:MDSIZTJP","canonical_record":{"source":{"id":"2409.06666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:34:34Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"7aa3dde4cb554c04e0b2c9377c3769a5a4d950348592f57f42a56143d900fb51","abstract_canon_sha256":"ed8da009c68bc81978b8447384d9cd5979a4a4fe14306e1551e5801aaea3387f"},"schema_version":"1.0"},"canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","source":{"kind":"arxiv","id":"2409.06666","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MDSIZTJPFN4ON7HW5HEUNDWHYZ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.06666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:34:34Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"7aa3dde4cb554c04e0b2c9377c3769a5a4d950348592f57f42a56143d900fb51","abstract_canon_sha256":"ed8da009c68bc81978b8447384d9cd5979a4a4fe14306e1551e5801aaea3387f"},"schema_version":"1.0"},"canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:04.358204Z","signature_b64":"83y7PwsUb+ZFmOPOIaLltLRd167ZUujz3cRElr4uqvogBuz1gF0unmLCkhPyqsmo2Xkne0nevYbIYjYuhy+GDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","last_reissued_at":"2026-07-05T10:22:04.357619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:04.357619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.06666","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vU56CKgigqg6B5WKh9IubIcG69MCKxB4NJjWZV2SPXv/88i8fisTDDCSLG8ZyFzS+Hto16O9n4ABMat6x1IMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T23:10:18.275387Z"},"content_sha256":"d8976295bce7931812821cd5bccaa9d4a3f98d9c6e54ab5ea622b81dfbaae39a","schema_version":"1.0","event_id":"sha256:d8976295bce7931812821cd5bccaa9d4a3f98d9c6e54ab5ea622b81dfbaae39a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MDSIZTJPFN4ON7HW5HEUNDWHYZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Yan Zhou, Zhengrui Ma","submitted_at":"2024-09-10T17:34:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06666","kind":"arxiv","version":2},"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/2409.06666/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ov2rxi2Om63YMh8vHUgKLmn3QjvE1S82CTv/QlnxOhvHyvF9K6v/Un9t4kl4FiUp2ld+QMs43N1n1i37zIRjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T23:10:18.276290Z"},"content_sha256":"a3d3fe89198548864b348976f2863810675aca21a9da1705877e51454aee0638","schema_version":"1.0","event_id":"sha256:a3d3fe89198548864b348976f2863810675aca21a9da1705877e51454aee0638"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/bundle.json","state_url":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T23:10:18Z","links":{"resolver":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ","bundle":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/bundle.json","state":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vEHQWv9yjNK7IR6/zH8RlV2TI7WmzLJIudVftZJlL6IHSSjzzEHEhusJGDFDUCT/iXfNwukykseLS40D8Y9ICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T23:10:18.280078Z","bundle_sha256":"1a056fac13e9b576a0db714d4fd7cf7d48812ff42004a54514a605bf4be7cec0"}}