{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H6FQWMT2OVM4PJKLOHNKADWXQP","short_pith_number":"pith:H6FQWMT2","canonical_record":{"source":{"id":"2408.02718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:56:41Z","cross_cats_sorted":[],"title_canon_sha256":"3c749d4667e7a792e1306d7e725985f99ff2fddbc2d8f25e06cf8af7833f9aac","abstract_canon_sha256":"e9124228370bb93b8afb617127a0413d9477d3faf5d4a20d27178dc5d5a0d29e"},"schema_version":"1.0"},"canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","source":{"kind":"arxiv","id":"2408.02718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02718","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02718v1","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02718","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"pith_short_12","alias_value":"H6FQWMT2OVM4","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"pith_short_16","alias_value":"H6FQWMT2OVM4PJKL","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"pith_short_8","alias_value":"H6FQWMT2","created_at":"2026-07-05T08:52:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H6FQWMT2OVM4PJKLOHNKADWXQP","target":"record","payload":{"canonical_record":{"source":{"id":"2408.02718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:56:41Z","cross_cats_sorted":[],"title_canon_sha256":"3c749d4667e7a792e1306d7e725985f99ff2fddbc2d8f25e06cf8af7833f9aac","abstract_canon_sha256":"e9124228370bb93b8afb617127a0413d9477d3faf5d4a20d27178dc5d5a0d29e"},"schema_version":"1.0"},"canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:39.161063Z","signature_b64":"SOIV/LJ7GpIBjhryUGV3/8oG3RsaH39JM8uND435e1vl+xXMWq/x3n3TNPAujPkz8/wPCaC8R5Dxi7u7De4zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","last_reissued_at":"2026-07-05T08:52:39.160572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:39.160572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.02718","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:52:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLzaHvhZi1v/Knv3IomAYUQaclnT7NVROIB1aE3FyfVDTFWm+cE1BFioc0a043LEunIE33cHEwcwYVOrYI4qCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:54.963632Z"},"content_sha256":"edad48b3e22aa0d652878b5e692df25760ee98e548b121a57e97c8bdc418c9c1","schema_version":"1.0","event_id":"sha256:edad48b3e22aa0d652878b5e692df25760ee98e548b121a57e97c8bdc418c9c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H6FQWMT2OVM4PJKLOHNKADWXQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Fanqing Meng, Hao Tian, Jiaqi Liao, Jifeng Dai, Jin Wang, Kaipeng Zhang, Ping Luo, Quanfeng Lu, Wenqi Shao, Xizhou Zhu, Yu Qiao","submitted_at":"2024-08-05T17:56:41Z","abstract_excerpt":"The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02718","kind":"arxiv","version":1},"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/2408.02718/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":"2026-07-05T08:52:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5U3jcvnKHXxbLFsiJ7ppGst8rzWv5nl7hh26/17SHnHY7UFP8DBgoXrZF54TQB1+xRhLMEHNN2L7aRjBkgQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:54.964017Z"},"content_sha256":"bbb57b28634e872fd48844eb8921b1f79a2d91e666424161aeb28dc04763f31c","schema_version":"1.0","event_id":"sha256:bbb57b28634e872fd48844eb8921b1f79a2d91e666424161aeb28dc04763f31c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/bundle.json","state_url":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/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":"2026-07-06T20:59:54Z","links":{"resolver":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP","bundle":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/bundle.json","state":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H6FQWMT2OVM4PJKLOHNKADWXQP","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":"e9124228370bb93b8afb617127a0413d9477d3faf5d4a20d27178dc5d5a0d29e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:56:41Z","title_canon_sha256":"3c749d4667e7a792e1306d7e725985f99ff2fddbc2d8f25e06cf8af7833f9aac"},"schema_version":"1.0","source":{"id":"2408.02718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02718","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02718v1","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02718","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"pith_short_12","alias_value":"H6FQWMT2OVM4","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"pith_short_16","alias_value":"H6FQWMT2OVM4PJKL","created_at":"2026-07-05T08:52:39Z"},{"alias_kind":"pith_short_8","alias_value":"H6FQWMT2","created_at":"2026-07-05T08:52:39Z"}],"graph_snapshots":[{"event_id":"sha256:bbb57b28634e872fd48844eb8921b1f79a2d91e666424161aeb28dc04763f31c","target":"graph","created_at":"2026-07-05T08:52:39Z","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/2408.02718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice que","authors_text":"Chuanhao Li, Fanqing Meng, Hao Tian, Jiaqi Liao, Jifeng Dai, Jin Wang, Kaipeng Zhang, Ping Luo, Quanfeng Lu, Wenqi Shao, Xizhou Zhu, Yu Qiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:56:41Z","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02718","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:edad48b3e22aa0d652878b5e692df25760ee98e548b121a57e97c8bdc418c9c1","target":"record","created_at":"2026-07-05T08:52:39Z","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":"e9124228370bb93b8afb617127a0413d9477d3faf5d4a20d27178dc5d5a0d29e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:56:41Z","title_canon_sha256":"3c749d4667e7a792e1306d7e725985f99ff2fddbc2d8f25e06cf8af7833f9aac"},"schema_version":"1.0","source":{"id":"2408.02718","kind":"arxiv","version":1}},"canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","first_computed_at":"2026-07-05T08:52:39.160572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:39.160572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOIV/LJ7GpIBjhryUGV3/8oG3RsaH39JM8uND435e1vl+xXMWq/x3n3TNPAujPkz8/wPCaC8R5Dxi7u7De4zBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:39.161063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edad48b3e22aa0d652878b5e692df25760ee98e548b121a57e97c8bdc418c9c1","sha256:bbb57b28634e872fd48844eb8921b1f79a2d91e666424161aeb28dc04763f31c"],"state_sha256":"f993eb14dfccf2b2a6c5242a9bd54bb8edc8d9d8233db7c5da7139817bb83ff1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UFyoGSioHIc4tVD2mjHAqv9ldsybRUBea/JXwaUixim/jatBz9Gzk/1lxhSMVjJsELvNznXo719BpYbQGCnCDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:59:54.966094Z","bundle_sha256":"c94bf85c16e4c07fefa4541e55bb7adbcff3b09b28779da023c20ceadec20573"}}