{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WPVZWI7A2G7D42XIMERHX4N6EL","short_pith_number":"pith:WPVZWI7A","schema_version":"1.0","canonical_sha256":"b3eb9b23e0d1be3e6ae861227bf1be22fb37c7e706c318ffdc2d61ee96ffab67","source":{"kind":"arxiv","id":"2406.11069","version":1},"attestation_state":"computed","paper":{"title":"WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bill Yuchen Lin, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, Yujie Lu","submitted_at":"2024-06-16T20:53:25Z","abstract_excerpt":"Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launched WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate VLMs. We curated WV-Bench by selecting 500 high-quality samples from 8,000 user submissions in WV-Arena. WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0.94 with the WV-Arena Elo. This significantly outperforms other benchmarks like MMVet, MMMU, and MMStar.\n  "},"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":"2406.11069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T20:53:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dcae5b41546b6ad524287916fd0080e7248e075d30d8b05a18e2f92fd2339c9e","abstract_canon_sha256":"e31c0ca9f328c39774b68c2acf34450f220a26d966b69fd41762ea883a92f466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:48.513840Z","signature_b64":"jNL2vkZ0dAqMzprHVWvEgosvRoiKu15jYVef8sGNHNrIhqofeizkcZCgDPxiqw7n7Q8Zz7K2WueRIJdSqgDgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3eb9b23e0d1be3e6ae861227bf1be22fb37c7e706c318ffdc2d61ee96ffab67","last_reissued_at":"2026-07-05T08:32:48.513429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:48.513429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bill Yuchen Lin, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, Yujie Lu","submitted_at":"2024-06-16T20:53:25Z","abstract_excerpt":"Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launched WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate VLMs. We curated WV-Bench by selecting 500 high-quality samples from 8,000 user submissions in WV-Arena. WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0.94 with the WV-Arena Elo. This significantly outperforms other benchmarks like MMVet, MMMU, and MMStar.\n  "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11069","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/2406.11069/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":"2406.11069","created_at":"2026-07-05T08:32:48.513484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11069v1","created_at":"2026-07-05T08:32:48.513484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11069","created_at":"2026-07-05T08:32:48.513484+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPVZWI7A2G7D","created_at":"2026-07-05T08:32:48.513484+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPVZWI7A2G7D42XI","created_at":"2026-07-05T08:32:48.513484+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPVZWI7A","created_at":"2026-07-05T08:32:48.513484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01671","citing_title":"When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2408.13257","citing_title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2503.05236","citing_title":"Unified Reward Model for Multimodal Understanding and Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09695","citing_title":"Assessing Privacy Preservation and Utility in Online Vision-Language Models","ref_index":4,"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":86,"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":171,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL","json":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL.json","graph_json":"https://pith.science/api/pith-number/WPVZWI7A2G7D42XIMERHX4N6EL/graph.json","events_json":"https://pith.science/api/pith-number/WPVZWI7A2G7D42XIMERHX4N6EL/events.json","paper":"https://pith.science/paper/WPVZWI7A"},"agent_actions":{"view_html":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL","download_json":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL.json","view_paper":"https://pith.science/paper/WPVZWI7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11069&json=true","fetch_graph":"https://pith.science/api/pith-number/WPVZWI7A2G7D42XIMERHX4N6EL/graph.json","fetch_events":"https://pith.science/api/pith-number/WPVZWI7A2G7D42XIMERHX4N6EL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL/action/storage_attestation","attest_author":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL/action/author_attestation","sign_citation":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL/action/citation_signature","submit_replication":"https://pith.science/pith/WPVZWI7A2G7D42XIMERHX4N6EL/action/replication_record"}},"created_at":"2026-07-05T08:32:48.513484+00:00","updated_at":"2026-07-05T08:32:48.513484+00:00"}