{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:24VY7DOQJES6X7AR3HDF5HR6U2","short_pith_number":"pith:24VY7DOQ","canonical_record":{"source":{"id":"2410.11190","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-15T02:10:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"title_canon_sha256":"a259a681ff0801580297ac53eef6deb18a2889d73caa043ad9c4653e8f24c7a5","abstract_canon_sha256":"97db3f566d788fbfbcfad572c7953728d9c8fc9764fadc42cc643ab1752f53ed"},"schema_version":"1.0"},"canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","source":{"kind":"arxiv","id":"2410.11190","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:24VY7DOQJES6X7AR3HDF5HR6U2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11190","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-15T02:10:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"title_canon_sha256":"a259a681ff0801580297ac53eef6deb18a2889d73caa043ad9c4653e8f24c7a5","abstract_canon_sha256":"97db3f566d788fbfbcfad572c7953728d9c8fc9764fadc42cc643ab1752f53ed"},"schema_version":"1.0"},"canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:09.310049Z","signature_b64":"7O1KfiLhtJmMz1fEVbRpjHQS8hRsxovdQsKSiiuSrRHgaebkTxNa9t8TEvIeHG47W5Zs130YzwJUrD8LK5jUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","last_reissued_at":"2026-07-05T09:31:09.309579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:09.309579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11190","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":"2026-07-05T09:31:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YDjcKIVZ8L2ffAebtUVEE5xmQrWds0Jq4yDV07saVu9vQZRawCwsOCQ9bbicxmlwVCBkC2isqynj23vbFuATDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:57:46.600839Z"},"content_sha256":"ada7dbdc40621b958092b0a4c4f11c0990f5eac29a6766d049bb5e86d8d1c0d7","schema_version":"1.0","event_id":"sha256:ada7dbdc40621b958092b0a4c4f11c0990f5eac29a6766d049bb5e86d8d1c0d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:24VY7DOQJES6X7AR3HDF5HR6U2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changqiao Wu, Zhifei Xie","submitted_at":"2024-10-15T02:10:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11190","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/2410.11190/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":"2026-07-05T09:31:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RPPN1QBvGX+aX82K2l+/YY37gRiMx7D3xiklEcYdUhTJMOaz8zPHtooQRl8Tg4a/P/dtewpuyq4kD3/BVknACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:57:46.601358Z"},"content_sha256":"ec9fd0808a0a7cc3fae124a66d46b45bcef241341e623baf2ff64eac765aaa1b","schema_version":"1.0","event_id":"sha256:ec9fd0808a0a7cc3fae124a66d46b45bcef241341e623baf2ff64eac765aaa1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/bundle.json","state_url":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24VY7DOQJES6X7AR3HDF5HR6U2/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":"2026-08-03T22:57:46Z","links":{"resolver":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2","bundle":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/bundle.json","state":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24VY7DOQJES6X7AR3HDF5HR6U2/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4u0s9t+xveG09xmozNpoLflKtT172JWzJ7p6SlQ8TG1uO4/XxeCfDVyvPZRHniK7rHWJARhmO/mJo9goDdjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:57:46.607034Z","bundle_sha256":"e38c7b1bb9afec9b77aa9f04db9f14068254050ac85f7ca523b98c919f9f3338"}}