{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JB4SQ6PIWNG64V6JNLTKKGRQEO","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":"91522856a6eed0c9082f18134cca9f207c79498bb9f20d47c3cfb213461b43f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:39:24Z","title_canon_sha256":"67b5838c78c9a0f38bc4f88b6cf03e70e992afabb0aa44fd86ad620ee3953130"},"schema_version":"1.0","source":{"id":"2306.09265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09265","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09265v1","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09265","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_12","alias_value":"JB4SQ6PIWNG6","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_16","alias_value":"JB4SQ6PIWNG64V6J","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_8","alias_value":"JB4SQ6PI","created_at":"2026-07-05T06:21:10Z"}],"graph_snapshots":[{"event_id":"sha256:c0f77167f6c51285236175fb8108da55400ed12c158110ba6947d42186c1ef9a","target":"graph","created_at":"2026-07-05T06:21:10Z","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/2306.09265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub). Our LVLM-eHub consists of $8$ representative LVLMs such as InstructBLIP and MiniGPT-4, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The former evaluates $6$ categories of multimodal capabilities of LVLMs such as v","authors_text":"Fanqing Meng, Kaipeng Zhang, Meng Lei, Peng Gao, Peng Xu, Ping Luo, Shuo Liu, Siyuan Huang, Wenqi Shao, Yu Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:39:24Z","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09265","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":"sha256:8910c1c7f0a302473262a80da7e6cde79d0a91af733fbe02bd1ec85015320c33","target":"record","created_at":"2026-07-05T06:21:10Z","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":"91522856a6eed0c9082f18134cca9f207c79498bb9f20d47c3cfb213461b43f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:39:24Z","title_canon_sha256":"67b5838c78c9a0f38bc4f88b6cf03e70e992afabb0aa44fd86ad620ee3953130"},"schema_version":"1.0","source":{"id":"2306.09265","kind":"arxiv","version":1}},"canonical_sha256":"48792879e8b34dee57c96ae6a51a3023abb514f34e5f1ec7d55b82174aa6a415","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48792879e8b34dee57c96ae6a51a3023abb514f34e5f1ec7d55b82174aa6a415","first_computed_at":"2026-07-05T06:21:10.405132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:10.405132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ut+CKJnKnCX4Dyy8ICazplYF43oPGf3uZIUlgAyOTiOF9QCg9Wmpr3H6cMj53sZsGE7Bb3Gb6KlF5YLlOiJTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:10.405564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8910c1c7f0a302473262a80da7e6cde79d0a91af733fbe02bd1ec85015320c33","sha256:c0f77167f6c51285236175fb8108da55400ed12c158110ba6947d42186c1ef9a"],"state_sha256":"5ba14c53d7cd88788688325a44eda01851a82d092f2e4051ce470fc010de7bae"}