{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VFJLSOAM3CGNICKSZE24KXGM3D","short_pith_number":"pith:VFJLSOAM","schema_version":"1.0","canonical_sha256":"a952b9380cd88cd40952c935c55cccd8d767bf1b950cd984570d4461edd29314","source":{"kind":"arxiv","id":"2407.11691","version":4},"attestation_state":"computed","paper":{"title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Agarwal, Chaoyou Fu, Dahua Lin, Enxin Song, Hailong Sun, Haodong Duan, Jiaqi Wang, Jixuan Chen, Junbo Cui, Junming Yang, Kai Chen, Lin Chen, Mo Li, Pan Zhang, Peiheng Zhou, Shengyuan Ding, Shiyin Lu, Song Mao, Tack Hwa Wong, Tianhao Liang, Weiyun Wang, Xiangyu Zhao, Xiaoyi Dong, Xiaozhe Li, Xinyu Fang, Yifan Zhang, Yuan Liu, Yubo Ma, Yuhang Zang, Yuxuan Qiao, Zhe Chen, Zicheng Zhang","submitted_at":"2024-07-16T13:06:15Z","abstract_excerpt":"We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluate existing multi-modality models and publish reproducible evaluation results. In VLMEvalKit, we implement over 200+ different large multi-modality models, including both proprietary APIs and open-source models, as well as more than 80 different multi-modal benchmarks. By implementing a single interface, new models can be easily added to the toolkit, while the toolkit automatica"},"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":"2407.11691","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T13:06:15Z","cross_cats_sorted":[],"title_canon_sha256":"3c3612b87ba498f53538166b0efa42399b4910ef683e8ae122d8724d4fd00ef5","abstract_canon_sha256":"d853d3f0fce3a32c55a3d1be00a278b9466d97b7839128c7d59dfd1198be2ded"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:43.451090Z","signature_b64":"pHrZS7WqeCTRdd4eaHUjZtO5kr7TufIDGWyd3k1ZKHvBEbhW4kPJkoSuQta1nreHBn0GbsKaecUsDZut7vT8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a952b9380cd88cd40952c935c55cccd8d767bf1b950cd984570d4461edd29314","last_reissued_at":"2026-07-05T12:00:43.450580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:43.450580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Agarwal, Chaoyou Fu, Dahua Lin, Enxin Song, Hailong Sun, Haodong Duan, Jiaqi Wang, Jixuan Chen, Junbo Cui, Junming Yang, Kai Chen, Lin Chen, Mo Li, Pan Zhang, Peiheng Zhou, Shengyuan Ding, Shiyin Lu, Song Mao, Tack Hwa Wong, Tianhao Liang, Weiyun Wang, Xiangyu Zhao, Xiaoyi Dong, Xiaozhe Li, Xinyu Fang, Yifan Zhang, Yuan Liu, Yubo Ma, Yuhang Zang, Yuxuan Qiao, Zhe Chen, Zicheng Zhang","submitted_at":"2024-07-16T13:06:15Z","abstract_excerpt":"We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluate existing multi-modality models and publish reproducible evaluation results. In VLMEvalKit, we implement over 200+ different large multi-modality models, including both proprietary APIs and open-source models, as well as more than 80 different multi-modal benchmarks. By implementing a single interface, new models can be easily added to the toolkit, while the toolkit automatica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11691","kind":"arxiv","version":4},"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/2407.11691/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":"2407.11691","created_at":"2026-07-05T12:00:43.450646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11691v4","created_at":"2026-07-05T12:00:43.450646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11691","created_at":"2026-07-05T12:00:43.450646+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFJLSOAM3CGN","created_at":"2026-07-05T12:00:43.450646+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFJLSOAM3CGNICKS","created_at":"2026-07-05T12:00:43.450646+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFJLSOAM","created_at":"2026-07-05T12:00:43.450646+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2607.05722","citing_title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17574","citing_title":"DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29531","citing_title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27446","citing_title":"Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27316","citing_title":"LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2505.16416","citing_title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16371","citing_title":"GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19461","citing_title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2509.10026","citing_title":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18512","citing_title":"S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models","ref_index":82,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D","json":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D.json","graph_json":"https://pith.science/api/pith-number/VFJLSOAM3CGNICKSZE24KXGM3D/graph.json","events_json":"https://pith.science/api/pith-number/VFJLSOAM3CGNICKSZE24KXGM3D/events.json","paper":"https://pith.science/paper/VFJLSOAM"},"agent_actions":{"view_html":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D","download_json":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D.json","view_paper":"https://pith.science/paper/VFJLSOAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11691&json=true","fetch_graph":"https://pith.science/api/pith-number/VFJLSOAM3CGNICKSZE24KXGM3D/graph.json","fetch_events":"https://pith.science/api/pith-number/VFJLSOAM3CGNICKSZE24KXGM3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D/action/storage_attestation","attest_author":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D/action/author_attestation","sign_citation":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D/action/citation_signature","submit_replication":"https://pith.science/pith/VFJLSOAM3CGNICKSZE24KXGM3D/action/replication_record"}},"created_at":"2026-07-05T12:00:43.450646+00:00","updated_at":"2026-07-05T12:00:43.450646+00:00"}