{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HLAVBY5AMPMCPJYHBRJUUESH7S","short_pith_number":"pith:HLAVBY5A","canonical_record":{"source":{"id":"2408.08632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T09:52:02Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"817d50fd02e0b0cef276840729a5812456025ee590012e8219ce5a04f012122c","abstract_canon_sha256":"abc53a326e61881018b120dec37ce7a7959e819e07d16bd751e59fe05cca9187"},"schema_version":"1.0"},"canonical_sha256":"3ac150e3a063d827a7070c534a1247fc8166f8a4213cf3f5772a916f866a3d34","source":{"kind":"arxiv","id":"2408.08632","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08632","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08632v2","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08632","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"HLAVBY5AMPMC","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"HLAVBY5AMPMCPJYH","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"HLAVBY5A","created_at":"2026-07-05T09:03:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HLAVBY5AMPMCPJYHBRJUUESH7S","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T09:52:02Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"817d50fd02e0b0cef276840729a5812456025ee590012e8219ce5a04f012122c","abstract_canon_sha256":"abc53a326e61881018b120dec37ce7a7959e819e07d16bd751e59fe05cca9187"},"schema_version":"1.0"},"canonical_sha256":"3ac150e3a063d827a7070c534a1247fc8166f8a4213cf3f5772a916f866a3d34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:55.319899Z","signature_b64":"CtCsu2hWO1Qfr/OxP07NRxpnAx5bzHy104UTXLasSMFyoRysNQ+LqslSxPh7r0IsNLvd03oNAix9ZvoJsKppBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac150e3a063d827a7070c534a1247fc8166f8a4213cf3f5772a916f866a3d34","last_reissued_at":"2026-07-05T09:03:55.319476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:55.319476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08632","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w5h30q4jLu0I/3FejiEbdrSMT1LXPFfwBmvMTI2o3Uxk81Im8H2pV/xrKrEWn9eFJFw9bqSj6OR6RQmGBGknBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T10:36:36.452825Z"},"content_sha256":"71b5f3a41d74b6d0d1abec3289563e573db0bbbde74a327ebcb6467f6d647ff1","schema_version":"1.0","event_id":"sha256:71b5f3a41d74b6d0d1abec3289563e573db0bbbde74a327ebcb6467f6d647ff1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HLAVBY5AMPMCPJYHBRJUUESH7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Benchmarks of Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chaoyou Fu, Chengjie Wang, Ding Qi, Hao Fei, Jian Li, Meng Luo, Ming Dai, Min Xia, Wankou Yang, Weiheng Lu, Yabiao Wang, Ying Tai, Yizhang Jin, Zhenye Gan","submitted_at":"2024-08-16T09:52:02Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are gaining increasing popularity in both academia and industry due to their remarkable performance in various applications such as visual question answering, visual perception, understanding, and reasoning. Over the past few years, significant efforts have been made to examine MLLMs from multiple perspectives. This paper presents a comprehensive review of 200 benchmarks and evaluations for MLLMs, focusing on (1)perception and understanding, (2)cognition and reasoning, (3)specific domains, (4)key capabilities, and (5)other modalities. Finally, we discus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08632","kind":"arxiv","version":2},"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/2408.08632/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":"2026-07-05T09:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XN5TTD0ihV+1lEJfZWVtcKr4p7aU7SZcmTjEQafu0Ls0K9NKpzOvTNec+KzX8W98voQb26Z7XxQ4B0o4hYLWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T10:36:36.453433Z"},"content_sha256":"f3d0cf59289b278c37f6b80e87f3019f11d21c61fa2d17e567dc37b0c291f4f0","schema_version":"1.0","event_id":"sha256:f3d0cf59289b278c37f6b80e87f3019f11d21c61fa2d17e567dc37b0c291f4f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLAVBY5AMPMCPJYHBRJUUESH7S/bundle.json","state_url":"https://pith.science/pith/HLAVBY5AMPMCPJYHBRJUUESH7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLAVBY5AMPMCPJYHBRJUUESH7S/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":"2026-08-03T10:36:36Z","links":{"resolver":"https://pith.science/pith/HLAVBY5AMPMCPJYHBRJUUESH7S","bundle":"https://pith.science/pith/HLAVBY5AMPMCPJYHBRJUUESH7S/bundle.json","state":"https://pith.science/pith/HLAVBY5AMPMCPJYHBRJUUESH7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLAVBY5AMPMCPJYHBRJUUESH7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HLAVBY5AMPMCPJYHBRJUUESH7S","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":"abc53a326e61881018b120dec37ce7a7959e819e07d16bd751e59fe05cca9187","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T09:52:02Z","title_canon_sha256":"817d50fd02e0b0cef276840729a5812456025ee590012e8219ce5a04f012122c"},"schema_version":"1.0","source":{"id":"2408.08632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08632","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08632v2","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08632","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"HLAVBY5AMPMC","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"HLAVBY5AMPMCPJYH","created_at":"2026-07-05T09:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"HLAVBY5A","created_at":"2026-07-05T09:03:55Z"}],"graph_snapshots":[{"event_id":"sha256:f3d0cf59289b278c37f6b80e87f3019f11d21c61fa2d17e567dc37b0c291f4f0","target":"graph","created_at":"2026-07-05T09:03:55Z","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/2408.08632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) are gaining increasing popularity in both academia and industry due to their remarkable performance in various applications such as visual question answering, visual perception, understanding, and reasoning. Over the past few years, significant efforts have been made to examine MLLMs from multiple perspectives. This paper presents a comprehensive review of 200 benchmarks and evaluations for MLLMs, focusing on (1)perception and understanding, (2)cognition and reasoning, (3)specific domains, (4)key capabilities, and (5)other modalities. Finally, we discus","authors_text":"Chaoyou Fu, Chengjie Wang, Ding Qi, Hao Fei, Jian Li, Meng Luo, Ming Dai, Min Xia, Wankou Yang, Weiheng Lu, Yabiao Wang, Ying Tai, Yizhang Jin, Zhenye Gan","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T09:52:02Z","title":"A Survey on Benchmarks of Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08632","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":"sha256:71b5f3a41d74b6d0d1abec3289563e573db0bbbde74a327ebcb6467f6d647ff1","target":"record","created_at":"2026-07-05T09:03:55Z","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":"abc53a326e61881018b120dec37ce7a7959e819e07d16bd751e59fe05cca9187","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T09:52:02Z","title_canon_sha256":"817d50fd02e0b0cef276840729a5812456025ee590012e8219ce5a04f012122c"},"schema_version":"1.0","source":{"id":"2408.08632","kind":"arxiv","version":2}},"canonical_sha256":"3ac150e3a063d827a7070c534a1247fc8166f8a4213cf3f5772a916f866a3d34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ac150e3a063d827a7070c534a1247fc8166f8a4213cf3f5772a916f866a3d34","first_computed_at":"2026-07-05T09:03:55.319476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:55.319476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CtCsu2hWO1Qfr/OxP07NRxpnAx5bzHy104UTXLasSMFyoRysNQ+LqslSxPh7r0IsNLvd03oNAix9ZvoJsKppBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:55.319899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71b5f3a41d74b6d0d1abec3289563e573db0bbbde74a327ebcb6467f6d647ff1","sha256:f3d0cf59289b278c37f6b80e87f3019f11d21c61fa2d17e567dc37b0c291f4f0"],"state_sha256":"d66e79fb4be4cad42c535a9cf3c0f4ca3cd3c38870c1c60a6beafe8e43232247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QUQTy7f0E7zGlQnr6XW4m8qwLj6wZaKF831PlJGKc6xrBoHdGHbuyxz6zui5Obj6N7yeS8S+VmTw92pRIBtaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T10:36:36.457313Z","bundle_sha256":"9cda8715ebeb0be8574239d10fe7948fd42c59f6a28aa495baf7992ace365001"}}