{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5GUTQ2N6CXGF4SNJZQT37CGG6F","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":"fb367b9b15f9a6169bf8e9549aa1742ebec4b3d044ca942bfec0e5d82b824a50","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T13:05:55Z","title_canon_sha256":"e5d09d22a3ca867b8c94e33ed3021f5a721f9f583677c727d4b10cd61beb89c0"},"schema_version":"1.0","source":{"id":"2408.15769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15769","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15769v1","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15769","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"5GUTQ2N6CXGF","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"5GUTQ2N6CXGF4SNJ","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"5GUTQ2N6","created_at":"2026-07-05T09:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:c27b16738a6beafc652bdf02891ae49ba8b7e595a43a9308bf6d8e5e4d67b909","target":"graph","created_at":"2026-07-05T09:00:17Z","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/2408.15769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) mimic human perception and reasoning system by integrating powerful Large Language Models (LLMs) with various modality encoders (e.g., vision, audio), positioning LLMs as the \"brain\" and various modality encoders as sensory organs. This framework endows MLLMs with human-like capabilities, and suggests a potential pathway towards achieving artificial general intelligence (AGI). With the emergence of all-round MLLMs like GPT-4V and Gemini, a multitude of evaluation methods have been developed to assess their capabilities across different dimensions. This ","authors_text":"Jiaxing Huang, Jingyi Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T13:05:55Z","title":"A Survey on Evaluation of Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15769","kind":"arxiv","version":1},"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":"sha256:6c39fa94c217890f2bbb5291ce7ce199f60c195dc0c53dd93fb740f99380ef0c","target":"record","created_at":"2026-07-05T09:00:17Z","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":"fb367b9b15f9a6169bf8e9549aa1742ebec4b3d044ca942bfec0e5d82b824a50","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T13:05:55Z","title_canon_sha256":"e5d09d22a3ca867b8c94e33ed3021f5a721f9f583677c727d4b10cd61beb89c0"},"schema_version":"1.0","source":{"id":"2408.15769","kind":"arxiv","version":1}},"canonical_sha256":"e9a93869be15cc5e49a9cc27bf88c6f1723d3340c182d65a6d4a023c96d31f5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9a93869be15cc5e49a9cc27bf88c6f1723d3340c182d65a6d4a023c96d31f5e","first_computed_at":"2026-07-05T09:00:17.168470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:17.168470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HePUzNx9d40hNAgM/x/ugynpUTWIy8X9YirZCh8evVQLJ2LwNOje/YEz5LbdIgp2FtvFxbZmtPsPHiFMzbTfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:17.168949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c39fa94c217890f2bbb5291ce7ce199f60c195dc0c53dd93fb740f99380ef0c","sha256:c27b16738a6beafc652bdf02891ae49ba8b7e595a43a9308bf6d8e5e4d67b909"],"state_sha256":"d93cb17495c3f2041a0027f121787f7df0229b24002c7f924d3e961b96424437"}