{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7XOWG4QH4V3OFWKQUJZC63UQCZ","short_pith_number":"pith:7XOWG4QH","canonical_record":{"source":{"id":"2411.00774","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-01T17:59:51Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"26d81c0e33aa21e498e22ea2144e71c18dbf28dc4c6d2cb1340045255c5ed51a","abstract_canon_sha256":"cbeb8fe77d91ea7748ccea21d53035a5b4b76d0ae1c4849256511aeeb3c97edc"},"schema_version":"1.0"},"canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","source":{"kind":"arxiv","id":"2411.00774","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00774","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00774v5","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00774","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"7XOWG4QH4V3O","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"7XOWG4QH4V3OFWKQ","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"7XOWG4QH","created_at":"2026-07-05T09:45:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7XOWG4QH4V3OFWKQUJZC63UQCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00774","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-01T17:59:51Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"26d81c0e33aa21e498e22ea2144e71c18dbf28dc4c6d2cb1340045255c5ed51a","abstract_canon_sha256":"cbeb8fe77d91ea7748ccea21d53035a5b4b76d0ae1c4849256511aeeb3c97edc"},"schema_version":"1.0"},"canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:57.069550Z","signature_b64":"zHT4DWXr+wlfnuIxX264KACViKCL+nSioiHaEFchyjr047ECflch/OK1FbOkhgS9aDY0whsgBrayqATJMFUXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","last_reissued_at":"2026-07-05T09:45:57.068979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:57.068979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00774","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHY1UstNplLEx8j2FSyTSo83JcWxrpkxriVT4e6jvWtFh+LBu+dbUKzCw1z7+v3VKqfQN+qhUMBVvhwsyA5rAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:11:58.645138Z"},"content_sha256":"1b1664ca435609afcb5c3bc4ca0c457b082763d4be2de1300f91922c95704b87","schema_version":"1.0","event_id":"sha256:1b1664ca435609afcb5c3bc4ca0c457b082763d4be2de1300f91922c95704b87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7XOWG4QH4V3OFWKQUJZC63UQCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoyou Fu, Ke Li, Lei Xie, Long Ma, Xing Sun, Xiong Wang, Yangze Li, Yunhang Shen","submitted_at":"2024-11-01T17:59:51Z","abstract_excerpt":"Rapidly developing large language models (LLMs) have brought tremendous intelligent applications. Especially, the GPT-4o's excellent duplex speech interaction ability has brought impressive experience to users. Researchers have recently proposed several multi-modal LLMs in this direction that can achieve user-agent speech-to-speech conversations. This paper proposes a novel speech-text multimodal LLM architecture called Freeze-Omni. Our main contribution is that the speech input and output modalities can be easily connected to a textual LLM while keeping the LLM's parameters frozen throughout "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00774","kind":"arxiv","version":5},"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/2411.00774/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":"2026-07-05T09:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBLv5LguqusgpARWUZYQnsfrldYxmCcGa7JvP3h5/zBgN+2C4a3vCAclMd5YSnl1b/TluPfklF08xdHiE2PMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:11:58.646095Z"},"content_sha256":"44672890e1b6f6b19b518a9181afc4e51eb4d61950c7a750ab9722406a332b8f","schema_version":"1.0","event_id":"sha256:44672890e1b6f6b19b518a9181afc4e51eb4d61950c7a750ab9722406a332b8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/bundle.json","state_url":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/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":"2026-08-03T16:11:58Z","links":{"resolver":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ","bundle":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/bundle.json","state":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7XOWG4QH4V3OFWKQUJZC63UQCZ","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":"cbeb8fe77d91ea7748ccea21d53035a5b4b76d0ae1c4849256511aeeb3c97edc","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-01T17:59:51Z","title_canon_sha256":"26d81c0e33aa21e498e22ea2144e71c18dbf28dc4c6d2cb1340045255c5ed51a"},"schema_version":"1.0","source":{"id":"2411.00774","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00774","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00774v5","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00774","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"7XOWG4QH4V3O","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"7XOWG4QH4V3OFWKQ","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"7XOWG4QH","created_at":"2026-07-05T09:45:57Z"}],"graph_snapshots":[{"event_id":"sha256:44672890e1b6f6b19b518a9181afc4e51eb4d61950c7a750ab9722406a332b8f","target":"graph","created_at":"2026-07-05T09:45:57Z","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/2411.00774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rapidly developing large language models (LLMs) have brought tremendous intelligent applications. Especially, the GPT-4o's excellent duplex speech interaction ability has brought impressive experience to users. Researchers have recently proposed several multi-modal LLMs in this direction that can achieve user-agent speech-to-speech conversations. This paper proposes a novel speech-text multimodal LLM architecture called Freeze-Omni. Our main contribution is that the speech input and output modalities can be easily connected to a textual LLM while keeping the LLM's parameters frozen throughout ","authors_text":"Chaoyou Fu, Ke Li, Lei Xie, Long Ma, Xing Sun, Xiong Wang, Yangze Li, Yunhang Shen","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-01T17:59:51Z","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00774","kind":"arxiv","version":5},"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":"sha256:1b1664ca435609afcb5c3bc4ca0c457b082763d4be2de1300f91922c95704b87","target":"record","created_at":"2026-07-05T09:45:57Z","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":"cbeb8fe77d91ea7748ccea21d53035a5b4b76d0ae1c4849256511aeeb3c97edc","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-01T17:59:51Z","title_canon_sha256":"26d81c0e33aa21e498e22ea2144e71c18dbf28dc4c6d2cb1340045255c5ed51a"},"schema_version":"1.0","source":{"id":"2411.00774","kind":"arxiv","version":5}},"canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","first_computed_at":"2026-07-05T09:45:57.068979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:57.068979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zHT4DWXr+wlfnuIxX264KACViKCL+nSioiHaEFchyjr047ECflch/OK1FbOkhgS9aDY0whsgBrayqATJMFUXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:57.069550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00774","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b1664ca435609afcb5c3bc4ca0c457b082763d4be2de1300f91922c95704b87","sha256:44672890e1b6f6b19b518a9181afc4e51eb4d61950c7a750ab9722406a332b8f"],"state_sha256":"ad0c6f95debce26e57c55b3fa0f0ba2ab71b1a9f2455709065cb21f1fea82198"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oaV57cFnHCP/JadUe2qnQsx4JZilB6BUhQCwIi11LbO7YNdbZnzAZukmpalFKMiBlj5n5zLyszIiHJumo+t1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:11:58.652424Z","bundle_sha256":"37a8addfe499877e747c9a4bcac46ab363f1cd8bb30639b06ac725b86c3e6d5f"}}