{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OQGIEJN4Q2MTEYX7AJD5POTLKD","short_pith_number":"pith:OQGIEJN4","canonical_record":{"source":{"id":"2407.15272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T21:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"5c2f5c3c1e9b8a2b5f38477053405e50a2362b770cf53bbd60617389b7d296b6","abstract_canon_sha256":"5d9f7c26f34ae4f644fa82d3ac09427ee9ca9c01acdc74a031ef6d6d6ccb119a"},"schema_version":"1.0"},"canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","source":{"kind":"arxiv","id":"2407.15272","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15272","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15272v2","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15272","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"OQGIEJN4Q2MT","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"OQGIEJN4Q2MTEYX7","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"OQGIEJN4","created_at":"2026-07-05T09:17:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OQGIEJN4Q2MTEYX7AJD5POTLKD","target":"record","payload":{"canonical_record":{"source":{"id":"2407.15272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T21:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"5c2f5c3c1e9b8a2b5f38477053405e50a2362b770cf53bbd60617389b7d296b6","abstract_canon_sha256":"5d9f7c26f34ae4f644fa82d3ac09427ee9ca9c01acdc74a031ef6d6d6ccb119a"},"schema_version":"1.0"},"canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:14.676690Z","signature_b64":"/ssfbQ/DeSGeiG/Kn5rVGfFoWMSy6j61sCtSiRQHQmZzUJcM9eMgpw5iEtssDbSGkX4Lf9FtMdQF7EcitOXlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","last_reissued_at":"2026-07-05T09:17:14.676131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:14.676131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.15272","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":"2026-07-05T09:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"962yeDNDqMIylDvreFhcqt2oSA9ee6UGrBK5H4qzY/wJoLupPdTrpA7bUP3ZDuPA3tpJS/n7CQDjiDWV1Uw8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:24:59.842033Z"},"content_sha256":"bee4cc09fb9fc35011185f0e1e9165d5695e2b8c94e1667345ae8afbf3b7d036","schema_version":"1.0","event_id":"sha256:bee4cc09fb9fc35011185f0e1e9165d5695e2b8c94e1667345ae8afbf3b7d036"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OQGIEJN4Q2MTEYX7AJD5POTLKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIBench: Evaluating Multimodal Large Language Models over Multiple Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chaoya Jiang, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Weiming Hu, Xi Zhang, Yaya Shi","submitted_at":"2024-07-21T21:22:58Z","abstract_excerpt":"Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored. Although a few benchmarks consider multiple images, their evaluation dimensions and samples are very limited. In this paper, we propose a new benchmark MIBench, to comprehensively evaluate fine-grained abilities of MLLMs in multi-image scenarios. Specifically, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15272","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/2407.15272/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":"2026-07-05T09:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWC2W5KhKmO3JrlkZC4KBtb45/na9OANYeIWTc+aYHlG9twi1Did1iQj8xSNdOT9sX91DR3LIzzGMhAGSxZJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:24:59.847595Z"},"content_sha256":"92b8b476e2d1f85c27f8509aba81609290cfc81933a65568e147f3406e686424","schema_version":"1.0","event_id":"sha256:92b8b476e2d1f85c27f8509aba81609290cfc81933a65568e147f3406e686424"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/bundle.json","state_url":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/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":"2026-08-12T18:24:59Z","links":{"resolver":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD","bundle":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/bundle.json","state":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OQGIEJN4Q2MTEYX7AJD5POTLKD","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":"5d9f7c26f34ae4f644fa82d3ac09427ee9ca9c01acdc74a031ef6d6d6ccb119a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T21:22:58Z","title_canon_sha256":"5c2f5c3c1e9b8a2b5f38477053405e50a2362b770cf53bbd60617389b7d296b6"},"schema_version":"1.0","source":{"id":"2407.15272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15272","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15272v2","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15272","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"OQGIEJN4Q2MT","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"OQGIEJN4Q2MTEYX7","created_at":"2026-07-05T09:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"OQGIEJN4","created_at":"2026-07-05T09:17:14Z"}],"graph_snapshots":[{"event_id":"sha256:92b8b476e2d1f85c27f8509aba81609290cfc81933a65568e147f3406e686424","target":"graph","created_at":"2026-07-05T09:17:14Z","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/2407.15272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored. Although a few benchmarks consider multiple images, their evaluation dimensions and samples are very limited. In this paper, we propose a new benchmark MIBench, to comprehensively evaluate fine-grained abilities of MLLMs in multi-image scenarios. Specifically, ","authors_text":"Bing Li, Chaoya Jiang, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Weiming Hu, Xi Zhang, Yaya Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T21:22:58Z","title":"MIBench: Evaluating Multimodal Large Language Models over Multiple Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15272","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:bee4cc09fb9fc35011185f0e1e9165d5695e2b8c94e1667345ae8afbf3b7d036","target":"record","created_at":"2026-07-05T09:17:14Z","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":"5d9f7c26f34ae4f644fa82d3ac09427ee9ca9c01acdc74a031ef6d6d6ccb119a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T21:22:58Z","title_canon_sha256":"5c2f5c3c1e9b8a2b5f38477053405e50a2362b770cf53bbd60617389b7d296b6"},"schema_version":"1.0","source":{"id":"2407.15272","kind":"arxiv","version":2}},"canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","first_computed_at":"2026-07-05T09:17:14.676131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:14.676131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ssfbQ/DeSGeiG/Kn5rVGfFoWMSy6j61sCtSiRQHQmZzUJcM9eMgpw5iEtssDbSGkX4Lf9FtMdQF7EcitOXlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:14.676690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bee4cc09fb9fc35011185f0e1e9165d5695e2b8c94e1667345ae8afbf3b7d036","sha256:92b8b476e2d1f85c27f8509aba81609290cfc81933a65568e147f3406e686424"],"state_sha256":"fb90058a305a8d4160e91aa2765516edc65bae16adb08293bb6520c3d7f08a73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NEBFocNPptJkce6kQvn11kjyyvvGuwAO58VpsBaCBQ/CoAuLbqeQuOnpAlbtKte7BHmkZVymzlRgU6JGMxmVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:24:59.864012Z","bundle_sha256":"9188cd34d22fd1fa5efa5b7c8ec15b26579a9ecec3f9ca9c2b7c91f146cc66cf"}}