{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PSQGL5I2BMMDRGZ4PGUT3VBOZL","short_pith_number":"pith:PSQGL5I2","canonical_record":{"source":{"id":"2406.12742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T16:02:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1e247e2c733b370c370bfe3897654b82e61c2981f3528a3f796d946d4c662fca","abstract_canon_sha256":"dda66027e61a66f35426934194c6dad4375587503de03c31943709c79d4de1a1"},"schema_version":"1.0"},"canonical_sha256":"7ca065f51a0b18389b3c79a93dd42ecaca5aef6ddabd15cddb8523f493030d5a","source":{"kind":"arxiv","id":"2406.12742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12742","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12742v1","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12742","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"PSQGL5I2BMMD","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"PSQGL5I2BMMDRGZ4","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"PSQGL5I2","created_at":"2026-07-05T08:33:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PSQGL5I2BMMDRGZ4PGUT3VBOZL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T16:02:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1e247e2c733b370c370bfe3897654b82e61c2981f3528a3f796d946d4c662fca","abstract_canon_sha256":"dda66027e61a66f35426934194c6dad4375587503de03c31943709c79d4de1a1"},"schema_version":"1.0"},"canonical_sha256":"7ca065f51a0b18389b3c79a93dd42ecaca5aef6ddabd15cddb8523f493030d5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:50.806472Z","signature_b64":"GueZ9MeOIyf71yxGF5weU7RrS7UlkmmzxAzz1ch02j4xpe0ifiK/lE9mK2ldSk0aA/aHWTfSKvFqLaVjZVbEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca065f51a0b18389b3c79a93dd42ecaca5aef6ddabd15cddb8523f493030d5a","last_reissued_at":"2026-07-05T08:33:50.806026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:50.806026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12742","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":"2026-07-05T08:33:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTx9D3WPdHQPLVOK3XveGtH9mrHa6jjP/d0VQwsNXg9eo5/t8aJyAkud/Xf0wjEOtefB4smOmxvSI9xTBi7FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:48:51.562979Z"},"content_sha256":"d0c93695c342aae87c88395aeb100624d6047f35e1d29dfcf4f97cc5c24c8c76","schema_version":"1.0","event_id":"sha256:d0c93695c342aae87c88395aeb100624d6047f35e1d29dfcf4f97cc5c24c8c76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PSQGL5I2BMMDRGZ4PGUT3VBOZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Letian Zhang, Timothy Hospedales, Yongshuo Zong","submitted_at":"2024-06-18T16:02:18Z","abstract_excerpt":"The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However, existing benchmarks for visual language models (VLMs) predominantly focus on single-image inputs, neglecting the crucial aspect of multi-image understanding. In this paper, we introduce a Multi-Image Relational Benchmark MIRB, designed to evaluate VLMs' ability to compare, analyze, and reason across multiple images. Our benchmark encompasses four categories: perce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12742","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/2406.12742/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":"2026-07-05T08:33:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zg7GbAYPVoKvqP7WzcSNkGd7XL9bfsn9dQGA3y+6f/C/lKAZIhOKV3+RlLJIdN2EKWSRiWA1Nn4yS3O8tw81Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:48:51.563477Z"},"content_sha256":"9b0482e14e1c26deeec2657cdad5eb1621ea9f040ce155dc6ff7b52437fbba5a","schema_version":"1.0","event_id":"sha256:9b0482e14e1c26deeec2657cdad5eb1621ea9f040ce155dc6ff7b52437fbba5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL/bundle.json","state_url":"https://pith.science/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL/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":"2026-08-07T19:48:51Z","links":{"resolver":"https://pith.science/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL","bundle":"https://pith.science/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL/bundle.json","state":"https://pith.science/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSQGL5I2BMMDRGZ4PGUT3VBOZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PSQGL5I2BMMDRGZ4PGUT3VBOZL","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":"dda66027e61a66f35426934194c6dad4375587503de03c31943709c79d4de1a1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T16:02:18Z","title_canon_sha256":"1e247e2c733b370c370bfe3897654b82e61c2981f3528a3f796d946d4c662fca"},"schema_version":"1.0","source":{"id":"2406.12742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12742","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12742v1","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12742","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"PSQGL5I2BMMD","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"PSQGL5I2BMMDRGZ4","created_at":"2026-07-05T08:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"PSQGL5I2","created_at":"2026-07-05T08:33:50Z"}],"graph_snapshots":[{"event_id":"sha256:9b0482e14e1c26deeec2657cdad5eb1621ea9f040ce155dc6ff7b52437fbba5a","target":"graph","created_at":"2026-07-05T08:33:50Z","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/2406.12742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However, existing benchmarks for visual language models (VLMs) predominantly focus on single-image inputs, neglecting the crucial aspect of multi-image understanding. In this paper, we introduce a Multi-Image Relational Benchmark MIRB, designed to evaluate VLMs' ability to compare, analyze, and reason across multiple images. Our benchmark encompasses four categories: perce","authors_text":"Bingchen Zhao, Letian Zhang, Timothy Hospedales, Yongshuo Zong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T16:02:18Z","title":"Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12742","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:d0c93695c342aae87c88395aeb100624d6047f35e1d29dfcf4f97cc5c24c8c76","target":"record","created_at":"2026-07-05T08:33:50Z","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":"dda66027e61a66f35426934194c6dad4375587503de03c31943709c79d4de1a1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T16:02:18Z","title_canon_sha256":"1e247e2c733b370c370bfe3897654b82e61c2981f3528a3f796d946d4c662fca"},"schema_version":"1.0","source":{"id":"2406.12742","kind":"arxiv","version":1}},"canonical_sha256":"7ca065f51a0b18389b3c79a93dd42ecaca5aef6ddabd15cddb8523f493030d5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ca065f51a0b18389b3c79a93dd42ecaca5aef6ddabd15cddb8523f493030d5a","first_computed_at":"2026-07-05T08:33:50.806026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:50.806026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GueZ9MeOIyf71yxGF5weU7RrS7UlkmmzxAzz1ch02j4xpe0ifiK/lE9mK2ldSk0aA/aHWTfSKvFqLaVjZVbEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:50.806472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0c93695c342aae87c88395aeb100624d6047f35e1d29dfcf4f97cc5c24c8c76","sha256:9b0482e14e1c26deeec2657cdad5eb1621ea9f040ce155dc6ff7b52437fbba5a"],"state_sha256":"22360fa9633c57442990c5ce28bac412ee59e0b05c9a387bd53e910ba53b914e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRX3YSqGx258G2UIyG6dbv2XdtRQlxE4FjIgLRkUBmu11uUhzrurZ6aAr5rPTvIuOyRtDSrbUZr3ws5XpeHzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:48:51.567260Z","bundle_sha256":"f7d25dd40989d3a21cbfa757592379a50d8ad7e74e46dea59d0a1611c7157c93"}}