{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVJWWNNIP5OYLFSQGSULWJVAIE","short_pith_number":"pith:TVJWWNNI","schema_version":"1.0","canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","source":{"kind":"arxiv","id":"2408.00765","version":2},"attestation_state":"computed","paper":{"title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Lingfeng Ren, Linjie Li, Weihao Yu, Xinchao Wang, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-08-01T17:59:54Z","abstract_excerpt":"MM-Vet, with open-ended vision-language questions targeting at evaluating integrated capabilities, has become one of the most popular benchmarks for large multimodal model evaluation. MM-Vet assesses six core vision-language (VL) capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math. However, its question format is restricted to single image-text pairs, lacking the interleaved image and text sequences prevalent in real-world scenarios. To address this limitation, we introduce MM-Vet v2, which includes a new VL capability called \"image-text sequence underst"},"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":"2408.00765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"89c12e4cba9bcce28519f7d07dd11ba63e7581a262f37291824d3b4a963a2a2e","abstract_canon_sha256":"f96eb4cfc88f1a04c86d7caea3154022c4609c407c81c796bd3eb909e2e8674b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:28.561532Z","signature_b64":"UaRVlVqWvytJKzI2hzTY4fjuXoXb3jJVFKv8ddn06z8UjBWN4hRaJIiAqx1pMT7/wVg/NR0nlV1eGtb5RXSpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","last_reissued_at":"2026-07-05T09:42:28.560986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:28.560986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Lingfeng Ren, Linjie Li, Weihao Yu, Xinchao Wang, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-08-01T17:59:54Z","abstract_excerpt":"MM-Vet, with open-ended vision-language questions targeting at evaluating integrated capabilities, has become one of the most popular benchmarks for large multimodal model evaluation. MM-Vet assesses six core vision-language (VL) capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math. However, its question format is restricted to single image-text pairs, lacking the interleaved image and text sequences prevalent in real-world scenarios. To address this limitation, we introduce MM-Vet v2, which includes a new VL capability called \"image-text sequence underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00765","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/2408.00765/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":"2408.00765","created_at":"2026-07-05T09:42:28.561044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00765v2","created_at":"2026-07-05T09:42:28.561044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00765","created_at":"2026-07-05T09:42:28.561044+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVJWWNNIP5OY","created_at":"2026-07-05T09:42:28.561044+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVJWWNNIP5OYLFSQ","created_at":"2026-07-05T09:42:28.561044+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVJWWNNI","created_at":"2026-07-05T09:42:28.561044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08194","citing_title":"Dive Into the Implicit Biases of Low-rank Vision-language Alignment","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18216","citing_title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20164","citing_title":"Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08846","citing_title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":285,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE","json":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE.json","graph_json":"https://pith.science/api/pith-number/TVJWWNNIP5OYLFSQGSULWJVAIE/graph.json","events_json":"https://pith.science/api/pith-number/TVJWWNNIP5OYLFSQGSULWJVAIE/events.json","paper":"https://pith.science/paper/TVJWWNNI"},"agent_actions":{"view_html":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE","download_json":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE.json","view_paper":"https://pith.science/paper/TVJWWNNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00765&json=true","fetch_graph":"https://pith.science/api/pith-number/TVJWWNNIP5OYLFSQGSULWJVAIE/graph.json","fetch_events":"https://pith.science/api/pith-number/TVJWWNNIP5OYLFSQGSULWJVAIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/action/storage_attestation","attest_author":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/action/author_attestation","sign_citation":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/action/citation_signature","submit_replication":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/action/replication_record"}},"created_at":"2026-07-05T09:42:28.561044+00:00","updated_at":"2026-07-05T09:42:28.561044+00:00"}