{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KBR4GOJO4GRHA4RFFRM5USCX2Z","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":"5624f4c6734c679eb367e2723b6ef6f05e94770bf845c90bcda165eb313c6f1e","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T17:59:31Z","title_canon_sha256":"52a30ce2210797f36d58f7c47a08434cb66550d30553dfe10c4630bc0d4e9577"},"schema_version":"1.0","source":{"id":"2408.15998","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15998","created_at":"2026-07-05T10:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15998v2","created_at":"2026-07-05T10:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15998","created_at":"2026-07-05T10:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"KBR4GOJO4GRH","created_at":"2026-07-05T10:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"KBR4GOJO4GRHA4RF","created_at":"2026-07-05T10:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"KBR4GOJO","created_at":"2026-07-05T10:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:d86ff2f05d4b3a94e462630660c4aa37c70c501b01b1456de0eea89e9a8dddc4","target":"graph","created_at":"2026-07-05T10:22:03Z","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/2408.15998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple visio","authors_text":"Andrew Tao, Bryan Catanzaro, De-An Huang, Fuxiao Liu, Guilin Liu, Hongxu Yin, Humphrey Shi, Jan Kautz, Karan Sapra, Min Shi, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yaser Yacoob, Yilin Zhao, Zhiding Yu","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T17:59:31Z","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15998","kind":"arxiv","version":2},"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":"sha256:54f85c18be9d9e25559730526dd7c02afd67b82e2d99f79a68afdcd11c850836","target":"record","created_at":"2026-07-05T10:22:03Z","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":"5624f4c6734c679eb367e2723b6ef6f05e94770bf845c90bcda165eb313c6f1e","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T17:59:31Z","title_canon_sha256":"52a30ce2210797f36d58f7c47a08434cb66550d30553dfe10c4630bc0d4e9577"},"schema_version":"1.0","source":{"id":"2408.15998","kind":"arxiv","version":2}},"canonical_sha256":"5063c3392ee1a27072252c59da4857d6688d03114d49134480688977e1e1190a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5063c3392ee1a27072252c59da4857d6688d03114d49134480688977e1e1190a","first_computed_at":"2026-07-05T10:22:03.765817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:03.765817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JrM02ZZui8CQdUoH2Od3B0Eu0dN6DxPsiBZro/4UWbUISP9eZCGNKXQM4/iT9Q7TTXkc5GYi2AMs3k6AEABcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:03.766402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15998","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54f85c18be9d9e25559730526dd7c02afd67b82e2d99f79a68afdcd11c850836","sha256:d86ff2f05d4b3a94e462630660c4aa37c70c501b01b1456de0eea89e9a8dddc4"],"state_sha256":"3cc7fb70978599cf0ce75be96301c6b2590ebac52c7055975b8702fa044a8a17"}