{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:24VY7DOQJES6X7AR3HDF5HR6U2","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":"97db3f566d788fbfbcfad572c7953728d9c8fc9764fadc42cc643ab1752f53ed","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-15T02:10:45Z","title_canon_sha256":"a259a681ff0801580297ac53eef6deb18a2889d73caa043ad9c4653e8f24c7a5"},"schema_version":"1.0","source":{"id":"2410.11190","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11190","created_at":"2026-07-05T09:31:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11190v3","created_at":"2026-07-05T09:31:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11190","created_at":"2026-07-05T09:31:09Z"},{"alias_kind":"pith_short_12","alias_value":"24VY7DOQJES6","created_at":"2026-07-05T09:31:09Z"},{"alias_kind":"pith_short_16","alias_value":"24VY7DOQJES6X7AR","created_at":"2026-07-05T09:31:09Z"},{"alias_kind":"pith_short_8","alias_value":"24VY7DOQ","created_at":"2026-07-05T09:31:09Z"}],"graph_snapshots":[{"event_id":"sha256:ec9fd0808a0a7cc3fae124a66d46b45bcef241341e623baf2ff64eac765aaa1b","target":"graph","created_at":"2026-07-05T09:31:09Z","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/2410.11190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"GPT-4o, an all-encompassing model, represents a milestone in the development of large multi-modal language models. It can understand visual, auditory, and textual modalities, directly output audio, and support flexible duplex interaction. Models from the open-source community often achieve some functionalities of GPT-4o, such as visual understanding and voice chat. Nevertheless, training a unified model that incorporates all modalities is challenging due to the complexities of multi-modal data, intricate model architectures, and training processes. In this paper, we introduce Mini-Omni2, a vis","authors_text":"Changqiao Wu, Zhifei Xie","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-15T02:10:45Z","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11190","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:ada7dbdc40621b958092b0a4c4f11c0990f5eac29a6766d049bb5e86d8d1c0d7","target":"record","created_at":"2026-07-05T09:31:09Z","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":"97db3f566d788fbfbcfad572c7953728d9c8fc9764fadc42cc643ab1752f53ed","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-15T02:10:45Z","title_canon_sha256":"a259a681ff0801580297ac53eef6deb18a2889d73caa043ad9c4653e8f24c7a5"},"schema_version":"1.0","source":{"id":"2410.11190","kind":"arxiv","version":3}},"canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","first_computed_at":"2026-07-05T09:31:09.309579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:09.309579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7O1KfiLhtJmMz1fEVbRpjHQS8hRsxovdQsKSiiuSrRHgaebkTxNa9t8TEvIeHG47W5Zs130YzwJUrD8LK5jUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:09.310049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11190","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ada7dbdc40621b958092b0a4c4f11c0990f5eac29a6766d049bb5e86d8d1c0d7","sha256:ec9fd0808a0a7cc3fae124a66d46b45bcef241341e623baf2ff64eac765aaa1b"],"state_sha256":"217be1c1b5f3e1b92cb3b7a829dd9c7812787d40cb1b47d8dc3ac8078162b49a"}