{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JQIYV4L2KXNGO23ZRARGWECZ2W","short_pith_number":"pith:JQIYV4L2","canonical_record":{"source":{"id":"2408.05211","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T17:59:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f7a795c5027e2dbf086e3746c0e60e1fc76f0a9aca306b60b869172b87e243a6","abstract_canon_sha256":"c22484306c0db67666708a9d20c75e816d5fd1d515ac590c9cf80e73e5e3bab7"},"schema_version":"1.0"},"canonical_sha256":"4c118af17a55da676b7988226b1059d59521f5c97bba404881296b62e693b595","source":{"kind":"arxiv","id":"2408.05211","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05211","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05211v3","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05211","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"JQIYV4L2KXNG","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"JQIYV4L2KXNGO23Z","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"JQIYV4L2","created_at":"2026-07-05T11:12:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JQIYV4L2KXNGO23ZRARGWECZ2W","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05211","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T17:59:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f7a795c5027e2dbf086e3746c0e60e1fc76f0a9aca306b60b869172b87e243a6","abstract_canon_sha256":"c22484306c0db67666708a9d20c75e816d5fd1d515ac590c9cf80e73e5e3bab7"},"schema_version":"1.0"},"canonical_sha256":"4c118af17a55da676b7988226b1059d59521f5c97bba404881296b62e693b595","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:19.186251Z","signature_b64":"ax5lQ2nqqjeD3lKB19g9H90EuAQtB8WB6MV20WreZFWHawzuYx+CV72Z+MPk45c0P3l+y0rJe2xck+NhjP9fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c118af17a55da676b7988226b1059d59521f5c97bba404881296b62e693b595","last_reissued_at":"2026-07-05T11:12:19.185753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:19.185753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05211","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":"2026-07-05T11:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"evMJ3u+rsoWgAkaTbLQdC06lQWdUxhcpU2M14OcEWutR5pjhZKqnJMOR7c2p0vnEipSWqVWQ0hRGqv4Ko0KwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T09:31:48.840280Z"},"content_sha256":"1007ac91165360073fabfeb6511f3b6dc4fca9f980eef1c0e2c1fdd1373a213d","schema_version":"1.0","event_id":"sha256:1007ac91165360073fabfeb6511f3b6dc4fca9f980eef1c0e2c1fdd1373a213d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JQIYV4L2KXNGO23ZRARGWECZ2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Chaoyou Fu, Di Yin, Haojia Lin, Haoyu Cao, Long Ma, Meng Zhao, Ran He, Rongrong Ji, Shaoqi Dong, Xiawu Zheng, Xing Sun, Xiong Wang, Yangze Li, Yi-Fan Zhang, Yuhang Dai, Yunhang Shen, Yunsheng Wu, Zuwei Long","submitted_at":"2024-08-09T17:59:49Z","abstract_excerpt":"The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05211","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/2408.05211/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":"2026-07-05T11:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qEpVrXqJGgnl9P7LuDayPfn8tQE1GwpebZFiP80Hgvyt5GzWXrbffhKMyxQZeLcrBvf7yb8f/d8P84FsagNRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T09:31:48.840674Z"},"content_sha256":"760e5f0c568697a081b797b3e33fe2215804a301f3d5817c08a430e87c12e182","schema_version":"1.0","event_id":"sha256:760e5f0c568697a081b797b3e33fe2215804a301f3d5817c08a430e87c12e182"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQIYV4L2KXNGO23ZRARGWECZ2W/bundle.json","state_url":"https://pith.science/pith/JQIYV4L2KXNGO23ZRARGWECZ2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQIYV4L2KXNGO23ZRARGWECZ2W/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":"2026-07-19T09:31:48Z","links":{"resolver":"https://pith.science/pith/JQIYV4L2KXNGO23ZRARGWECZ2W","bundle":"https://pith.science/pith/JQIYV4L2KXNGO23ZRARGWECZ2W/bundle.json","state":"https://pith.science/pith/JQIYV4L2KXNGO23ZRARGWECZ2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQIYV4L2KXNGO23ZRARGWECZ2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JQIYV4L2KXNGO23ZRARGWECZ2W","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":"c22484306c0db67666708a9d20c75e816d5fd1d515ac590c9cf80e73e5e3bab7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T17:59:49Z","title_canon_sha256":"f7a795c5027e2dbf086e3746c0e60e1fc76f0a9aca306b60b869172b87e243a6"},"schema_version":"1.0","source":{"id":"2408.05211","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05211","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05211v3","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05211","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"JQIYV4L2KXNG","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"JQIYV4L2KXNGO23Z","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"JQIYV4L2","created_at":"2026-07-05T11:12:19Z"}],"graph_snapshots":[{"event_id":"sha256:760e5f0c568697a081b797b3e33fe2215804a301f3d5817c08a430e87c12e182","target":"graph","created_at":"2026-07-05T11:12:19Z","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/2408.05211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model","authors_text":"Caifeng Shan, Chaoyou Fu, Di Yin, Haojia Lin, Haoyu Cao, Long Ma, Meng Zhao, Ran He, Rongrong Ji, Shaoqi Dong, Xiawu Zheng, Xing Sun, Xiong Wang, Yangze Li, Yi-Fan Zhang, Yuhang Dai, Yunhang Shen, Yunsheng Wu, Zuwei Long","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T17:59:49Z","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05211","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":"sha256:1007ac91165360073fabfeb6511f3b6dc4fca9f980eef1c0e2c1fdd1373a213d","target":"record","created_at":"2026-07-05T11:12:19Z","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":"c22484306c0db67666708a9d20c75e816d5fd1d515ac590c9cf80e73e5e3bab7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T17:59:49Z","title_canon_sha256":"f7a795c5027e2dbf086e3746c0e60e1fc76f0a9aca306b60b869172b87e243a6"},"schema_version":"1.0","source":{"id":"2408.05211","kind":"arxiv","version":3}},"canonical_sha256":"4c118af17a55da676b7988226b1059d59521f5c97bba404881296b62e693b595","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c118af17a55da676b7988226b1059d59521f5c97bba404881296b62e693b595","first_computed_at":"2026-07-05T11:12:19.185753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:19.185753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ax5lQ2nqqjeD3lKB19g9H90EuAQtB8WB6MV20WreZFWHawzuYx+CV72Z+MPk45c0P3l+y0rJe2xck+NhjP9fCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:19.186251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05211","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1007ac91165360073fabfeb6511f3b6dc4fca9f980eef1c0e2c1fdd1373a213d","sha256:760e5f0c568697a081b797b3e33fe2215804a301f3d5817c08a430e87c12e182"],"state_sha256":"964e39a05212c0aeef823d69bfc6ee222a13cc93f0b3e93e57ff0772ba039fcf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joa0iJgKvgZFipBhAKkp9Rja69JURxamqpbwLj6c3C3OfdlQS/7P5UfXhlBL6re2UqyhHVWI/KFpQg88eatKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T09:31:48.842823Z","bundle_sha256":"96c6e0c88a20b0f4c088a6f2dbe7c4df6331ee22028917f124b7e01cfc9e61e8"}}