{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N5NXAVR4OWEDOROH6COBBM2YRG","short_pith_number":"pith:N5NXAVR4","canonical_record":{"source":{"id":"2408.16725","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-29T17:18:53Z","cross_cats_sorted":["cs.CL","cs.HC","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"24dffb17c87c05938e380dbff747987998b2a94d40b21809964635d755939569","abstract_canon_sha256":"2af68310aaba36bea4535adc8b1be03cd41de365c26ae3df6e0f0ef42b9dce18"},"schema_version":"1.0"},"canonical_sha256":"6f5b70563c75883745c7f09c10b35889981d341b874befb4253b209317e3bbfe","source":{"kind":"arxiv","id":"2408.16725","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16725","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16725v3","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16725","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_12","alias_value":"N5NXAVR4OWED","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_16","alias_value":"N5NXAVR4OWEDOROH","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_8","alias_value":"N5NXAVR4","created_at":"2026-07-05T09:31:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N5NXAVR4OWEDOROH6COBBM2YRG","target":"record","payload":{"canonical_record":{"source":{"id":"2408.16725","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-29T17:18:53Z","cross_cats_sorted":["cs.CL","cs.HC","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"24dffb17c87c05938e380dbff747987998b2a94d40b21809964635d755939569","abstract_canon_sha256":"2af68310aaba36bea4535adc8b1be03cd41de365c26ae3df6e0f0ef42b9dce18"},"schema_version":"1.0"},"canonical_sha256":"6f5b70563c75883745c7f09c10b35889981d341b874befb4253b209317e3bbfe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:07.424241Z","signature_b64":"Pti9kVgrRVuIPE0WuJXDE+FTfAYu92/KpWVyrSViYLkoA++bhB7Iz2I11m899tWwhN9xDGv7J3yKHKmnZ6dDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f5b70563c75883745c7f09c10b35889981d341b874befb4253b209317e3bbfe","last_reissued_at":"2026-07-05T09:31:07.423759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:07.423759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.16725","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2UeebqBnE8BKQVWuzfzFA/1B+jpSAHtE/+aSYh13uikzBdmjH9Alnz5DBt1hZiWFHiKepL+z8sFhaiwO397mDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:42:30.826379Z"},"content_sha256":"34087603724c497313458e685c6093e25b9ae2e75eb2c38fd66bd489095de0f9","schema_version":"1.0","event_id":"sha256:34087603724c497313458e685c6093e25b9ae2e75eb2c38fd66bd489095de0f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N5NXAVR4OWEDOROH6COBBM2YRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Changqiao Wu, Zhifei Xie","submitted_at":"2024-08-29T17:18:53Z","abstract_excerpt":"Recent advances in language models have achieved significant progress. GPT-4o, as a new milestone, has enabled real-time conversations with humans, demonstrating near-human natural fluency. Such human-computer interaction necessitates models with the capability to perform reasoning directly with the audio modality and generate output in streaming. However, this remains beyond the reach of current academic models, as they typically depend on extra TTS systems for speech synthesis, resulting in undesirable latency. This paper introduces the Mini-Omni, an audio-based end-to-end conversational mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16725","kind":"arxiv","version":3},"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/2408.16725/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":"2026-07-05T09:31:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJGcMS/nm/v8sPepi2CpcQQ4ptXTa3KgtYIammVvXogFjYZNEHXCnlQEYipl711sFMrGIIvl2KjTQXbuZGjLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:42:30.827079Z"},"content_sha256":"8f0b7ceba883c8a13988a6e3ece2b00f8c6bb6c994bc61423d7529e28bcb2e4c","schema_version":"1.0","event_id":"sha256:8f0b7ceba883c8a13988a6e3ece2b00f8c6bb6c994bc61423d7529e28bcb2e4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5NXAVR4OWEDOROH6COBBM2YRG/bundle.json","state_url":"https://pith.science/pith/N5NXAVR4OWEDOROH6COBBM2YRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5NXAVR4OWEDOROH6COBBM2YRG/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":"2026-08-04T09:42:30Z","links":{"resolver":"https://pith.science/pith/N5NXAVR4OWEDOROH6COBBM2YRG","bundle":"https://pith.science/pith/N5NXAVR4OWEDOROH6COBBM2YRG/bundle.json","state":"https://pith.science/pith/N5NXAVR4OWEDOROH6COBBM2YRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5NXAVR4OWEDOROH6COBBM2YRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N5NXAVR4OWEDOROH6COBBM2YRG","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":"2af68310aaba36bea4535adc8b1be03cd41de365c26ae3df6e0f0ef42b9dce18","cross_cats_sorted":["cs.CL","cs.HC","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-29T17:18:53Z","title_canon_sha256":"24dffb17c87c05938e380dbff747987998b2a94d40b21809964635d755939569"},"schema_version":"1.0","source":{"id":"2408.16725","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16725","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16725v3","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16725","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_12","alias_value":"N5NXAVR4OWED","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_16","alias_value":"N5NXAVR4OWEDOROH","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_8","alias_value":"N5NXAVR4","created_at":"2026-07-05T09:31:07Z"}],"graph_snapshots":[{"event_id":"sha256:8f0b7ceba883c8a13988a6e3ece2b00f8c6bb6c994bc61423d7529e28bcb2e4c","target":"graph","created_at":"2026-07-05T09:31:07Z","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/2408.16725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language models have achieved significant progress. GPT-4o, as a new milestone, has enabled real-time conversations with humans, demonstrating near-human natural fluency. Such human-computer interaction necessitates models with the capability to perform reasoning directly with the audio modality and generate output in streaming. However, this remains beyond the reach of current academic models, as they typically depend on extra TTS systems for speech synthesis, resulting in undesirable latency. This paper introduces the Mini-Omni, an audio-based end-to-end conversational mod","authors_text":"Changqiao Wu, Zhifei Xie","cross_cats":["cs.CL","cs.HC","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-29T17:18:53Z","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16725","kind":"arxiv","version":3},"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":"sha256:34087603724c497313458e685c6093e25b9ae2e75eb2c38fd66bd489095de0f9","target":"record","created_at":"2026-07-05T09:31:07Z","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":"2af68310aaba36bea4535adc8b1be03cd41de365c26ae3df6e0f0ef42b9dce18","cross_cats_sorted":["cs.CL","cs.HC","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-29T17:18:53Z","title_canon_sha256":"24dffb17c87c05938e380dbff747987998b2a94d40b21809964635d755939569"},"schema_version":"1.0","source":{"id":"2408.16725","kind":"arxiv","version":3}},"canonical_sha256":"6f5b70563c75883745c7f09c10b35889981d341b874befb4253b209317e3bbfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f5b70563c75883745c7f09c10b35889981d341b874befb4253b209317e3bbfe","first_computed_at":"2026-07-05T09:31:07.423759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:07.423759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pti9kVgrRVuIPE0WuJXDE+FTfAYu92/KpWVyrSViYLkoA++bhB7Iz2I11m899tWwhN9xDGv7J3yKHKmnZ6dDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:07.424241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16725","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34087603724c497313458e685c6093e25b9ae2e75eb2c38fd66bd489095de0f9","sha256:8f0b7ceba883c8a13988a6e3ece2b00f8c6bb6c994bc61423d7529e28bcb2e4c"],"state_sha256":"3b7e7a1216ccbb8f85f951540078bc25aed54a05cf0420bccd7a62359ef09fd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LGqqnF9TRtAI9AUaG2GuL7BAOkKVx3QO9Lvaa3Q3+fnVEZmA7xtZ7NTblw0a5+yeo7AsjSypjDCbvtx1lN+VDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:42:30.833581Z","bundle_sha256":"865765a3002ec9efa13299d206bfff4d65a6758d9b23ed3d81f6cf87a4ea3321"}}