{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JB4SQ6PIWNG64V6JNLTKKGRQEO","short_pith_number":"pith:JB4SQ6PI","schema_version":"1.0","canonical_sha256":"48792879e8b34dee57c96ae6a51a3023abb514f34e5f1ec7d55b82174aa6a415","source":{"kind":"arxiv","id":"2306.09265","version":1},"attestation_state":"computed","paper":{"title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fanqing Meng, Kaipeng Zhang, Meng Lei, Peng Gao, Peng Xu, Ping Luo, Shuo Liu, Siyuan Huang, Wenqi Shao, Yu Qiao","submitted_at":"2023-06-15T16:39:24Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.09265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:39:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67b5838c78c9a0f38bc4f88b6cf03e70e992afabb0aa44fd86ad620ee3953130","abstract_canon_sha256":"91522856a6eed0c9082f18134cca9f207c79498bb9f20d47c3cfb213461b43f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:10.405564Z","signature_b64":"Ut+CKJnKnCX4Dyy8ICazplYF43oPGf3uZIUlgAyOTiOF9QCg9Wmpr3H6cMj53sZsGE7Bb3Gb6KlF5YLlOiJTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48792879e8b34dee57c96ae6a51a3023abb514f34e5f1ec7d55b82174aa6a415","last_reissued_at":"2026-07-05T06:21:10.405132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:10.405132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fanqing Meng, Kaipeng Zhang, Meng Lei, Peng Gao, Peng Xu, Ping Luo, Shuo Liu, Siyuan Huang, Wenqi Shao, Yu Qiao","submitted_at":"2023-06-15T16:39:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09265","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/2306.09265/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.09265","created_at":"2026-07-05T06:21:10.405187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09265v1","created_at":"2026-07-05T06:21:10.405187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09265","created_at":"2026-07-05T06:21:10.405187+00:00"},{"alias_kind":"pith_short_12","alias_value":"JB4SQ6PIWNG6","created_at":"2026-07-05T06:21:10.405187+00:00"},{"alias_kind":"pith_short_16","alias_value":"JB4SQ6PIWNG64V6J","created_at":"2026-07-05T06:21:10.405187+00:00"},{"alias_kind":"pith_short_8","alias_value":"JB4SQ6PI","created_at":"2026-07-05T06:21:10.405187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19706","citing_title":"NEST: Narrative Event Structures in Time for Long Video Understanding","ref_index":287,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2308.12067","citing_title":"MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14194","citing_title":"VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2403.00476","citing_title":"TempCompass: Do Video LLMs Really Understand Videos?","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14624","citing_title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13173","citing_title":"OxyEcomBench: Benchmarking Multimodal Foundation Models across E-Commerce Ecosystems","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02813","citing_title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2307.16125","citing_title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO","json":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO.json","graph_json":"https://pith.science/api/pith-number/JB4SQ6PIWNG64V6JNLTKKGRQEO/graph.json","events_json":"https://pith.science/api/pith-number/JB4SQ6PIWNG64V6JNLTKKGRQEO/events.json","paper":"https://pith.science/paper/JB4SQ6PI"},"agent_actions":{"view_html":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO","download_json":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO.json","view_paper":"https://pith.science/paper/JB4SQ6PI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09265&json=true","fetch_graph":"https://pith.science/api/pith-number/JB4SQ6PIWNG64V6JNLTKKGRQEO/graph.json","fetch_events":"https://pith.science/api/pith-number/JB4SQ6PIWNG64V6JNLTKKGRQEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO/action/storage_attestation","attest_author":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO/action/author_attestation","sign_citation":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO/action/citation_signature","submit_replication":"https://pith.science/pith/JB4SQ6PIWNG64V6JNLTKKGRQEO/action/replication_record"}},"created_at":"2026-07-05T06:21:10.405187+00:00","updated_at":"2026-07-05T06:21:10.405187+00:00"}