{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JN7XZV5VVXWWJXMQHSPQMOCMCR","short_pith_number":"pith:JN7XZV5V","canonical_record":{"source":{"id":"2409.18042","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:44:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2a4f7bb0388078035335c5241d81e5dfe96a743c7446dd1df01d81fa2d99f04e","abstract_canon_sha256":"904542ee6204d62d17956439b01c78462fe4baf78fd6e15495365e1a66b50c05"},"schema_version":"1.0"},"canonical_sha256":"4b7f7cd7b5aded64dd903c9f06384c147244b7e1e600cf6183cc93963c809415","source":{"kind":"arxiv","id":"2409.18042","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18042","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18042v4","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18042","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"JN7XZV5VVXWW","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"JN7XZV5VVXWWJXMQ","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"JN7XZV5V","created_at":"2026-07-05T10:35:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JN7XZV5VVXWWJXMQHSPQMOCMCR","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18042","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:44:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2a4f7bb0388078035335c5241d81e5dfe96a743c7446dd1df01d81fa2d99f04e","abstract_canon_sha256":"904542ee6204d62d17956439b01c78462fe4baf78fd6e15495365e1a66b50c05"},"schema_version":"1.0"},"canonical_sha256":"4b7f7cd7b5aded64dd903c9f06384c147244b7e1e600cf6183cc93963c809415","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:36.386714Z","signature_b64":"AfU4F05P5VHQtYNE4Hiu2vihtq0WfcMfKwI0c4+8+KwSIau7aRqQe/5iLJyPFPP/qPfx/X5RDMyKGtFQ5sUwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b7f7cd7b5aded64dd903c9f06384c147244b7e1e600cf6183cc93963c809415","last_reissued_at":"2026-07-05T10:35:36.386190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:36.386190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18042","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVSKxkPVWKYT6W2M0CsUdt14BhMjopRb6rtdYjLeBtE20DlyD9JwPgKXNAQBNNvHIDqNEudZ1YoOapXbB6S7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:07:06.131537Z"},"content_sha256":"543eafb4ec19971e2b7b01114c28a6aa7eecbf9e2664149092974ccdd245b0a3","schema_version":"1.0","event_id":"sha256:543eafb4ec19971e2b7b01114c28a6aa7eecbf9e2664149092974ccdd245b0a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JN7XZV5VVXWWJXMQHSPQMOCMCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunwei Wang, Daxin Tan, Dingdong Wang, Dit-Yan Yeung, Hang Xu, Haoli Bai, Haoyuan Li, Hengshuang Zhao, James T. Kwok, Jianhua Han, Jing Xu, Jun Yao, Kai Chen, Kun Xiang, Kuo Yang, Lanqing Hong, Lu Hou, Nian Xie, Qun Liu, Runhui Huang, Weike Jin, Wei Zhang, Xiao Chen, Xiaodan Liang, Xiaohui Li, Yihan Zeng, Yi Zhu, Yunhao Gou, Yu Zhang, Zhenguo Li, Zhili Liu","submitted_at":"2024-09-26T16:44:02Z","abstract_excerpt":"GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging for the open-source community. Existing vision-language models rely on external tools for speech processing, while speech-language models still suffer from limited or totally without vision-understanding capabilities. To address this gap, we propose the EMOVA (EMotionally Omni-present Voice Assista"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18042","kind":"arxiv","version":4},"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/2409.18042/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":"2026-07-05T10:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"He+Pmh0FvWJwPvPb6cGL1P7cMAsGbcLhIMGFbLCwi4/TT+kTsUKRVnrAv9nV4PDb29IBdfA6BrLUpFnVDyWeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:07:06.132055Z"},"content_sha256":"9ead72e230e794acfd018dd8bfce180c643c0bcf2644b36213611f85e4a23dd9","schema_version":"1.0","event_id":"sha256:9ead72e230e794acfd018dd8bfce180c643c0bcf2644b36213611f85e4a23dd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR/bundle.json","state_url":"https://pith.science/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR/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":"2026-08-04T04:07:06Z","links":{"resolver":"https://pith.science/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR","bundle":"https://pith.science/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR/bundle.json","state":"https://pith.science/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JN7XZV5VVXWWJXMQHSPQMOCMCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JN7XZV5VVXWWJXMQHSPQMOCMCR","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":"904542ee6204d62d17956439b01c78462fe4baf78fd6e15495365e1a66b50c05","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:44:02Z","title_canon_sha256":"2a4f7bb0388078035335c5241d81e5dfe96a743c7446dd1df01d81fa2d99f04e"},"schema_version":"1.0","source":{"id":"2409.18042","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18042","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18042v4","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18042","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"JN7XZV5VVXWW","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"JN7XZV5VVXWWJXMQ","created_at":"2026-07-05T10:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"JN7XZV5V","created_at":"2026-07-05T10:35:36Z"}],"graph_snapshots":[{"event_id":"sha256:9ead72e230e794acfd018dd8bfce180c643c0bcf2644b36213611f85e4a23dd9","target":"graph","created_at":"2026-07-05T10:35:36Z","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/2409.18042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging for the open-source community. Existing vision-language models rely on external tools for speech processing, while speech-language models still suffer from limited or totally without vision-understanding capabilities. To address this gap, we propose the EMOVA (EMotionally Omni-present Voice Assista","authors_text":"Chunwei Wang, Daxin Tan, Dingdong Wang, Dit-Yan Yeung, Hang Xu, Haoli Bai, Haoyuan Li, Hengshuang Zhao, James T. Kwok, Jianhua Han, Jing Xu, Jun Yao, Kai Chen, Kun Xiang, Kuo Yang, Lanqing Hong, Lu Hou, Nian Xie, Qun Liu, Runhui Huang, Weike Jin, Wei Zhang, Xiao Chen, Xiaodan Liang, Xiaohui Li, Yihan Zeng, Yi Zhu, Yunhao Gou, Yu Zhang, Zhenguo Li, Zhili Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:44:02Z","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18042","kind":"arxiv","version":4},"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":"sha256:543eafb4ec19971e2b7b01114c28a6aa7eecbf9e2664149092974ccdd245b0a3","target":"record","created_at":"2026-07-05T10:35:36Z","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":"904542ee6204d62d17956439b01c78462fe4baf78fd6e15495365e1a66b50c05","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:44:02Z","title_canon_sha256":"2a4f7bb0388078035335c5241d81e5dfe96a743c7446dd1df01d81fa2d99f04e"},"schema_version":"1.0","source":{"id":"2409.18042","kind":"arxiv","version":4}},"canonical_sha256":"4b7f7cd7b5aded64dd903c9f06384c147244b7e1e600cf6183cc93963c809415","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b7f7cd7b5aded64dd903c9f06384c147244b7e1e600cf6183cc93963c809415","first_computed_at":"2026-07-05T10:35:36.386190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:36.386190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfU4F05P5VHQtYNE4Hiu2vihtq0WfcMfKwI0c4+8+KwSIau7aRqQe/5iLJyPFPP/qPfx/X5RDMyKGtFQ5sUwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:36.386714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18042","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543eafb4ec19971e2b7b01114c28a6aa7eecbf9e2664149092974ccdd245b0a3","sha256:9ead72e230e794acfd018dd8bfce180c643c0bcf2644b36213611f85e4a23dd9"],"state_sha256":"e15c1d2e0c74ce11c56572c6971e6051bbb2de3aad0d04f09b8e483d365920ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7XYJZQ8VyHaVwUSy8uPItOElSOOTwlTP20ivNtJWY+nKiX6zLXMQO9oLSYWhFUghBukxm7R+cY/NsmqBZB4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:07:06.135566Z","bundle_sha256":"9520b17249bb6a6a7806548c020c61b73797c34304cd1ff1aa3aa1a3873c9e3b"}}