{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WUTSVMJINFWJR24R4HXUJHO5ZF","short_pith_number":"pith:WUTSVMJI","schema_version":"1.0","canonical_sha256":"b5272ab128696c98eb91e1ef449dddc9561ed867e9465c31b8b435378f3340a8","source":{"kind":"arxiv","id":"2404.05955","version":1},"attestation_state":"computed","paper":{"title":"VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bill Yuchen Lin, Graham Neubig, Junpeng Liu, Wai Lam, Xiang Yue, Yifan Song, Yuanzhi Li","submitted_at":"2024-04-09T02:29:39Z","abstract_excerpt":"Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed for general multimodal tasks, failing to capture the unique characteristics of web pages, or focus on end-to-end web agent tasks, unable to measure fine-grained abilities such as OCR, understanding, and grounding. In this paper, we introduce \\bench{}, a multimodal benchmark designed to assess the capabilities of MLLMs across a variety of web tasks. \\bench{} co"},"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":"2404.05955","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T02:29:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a413b1d90e7119e3703aaabac932d21672586306d4efe788164a8dcb5604bbd9","abstract_canon_sha256":"713576a384e64557f8d9365e33662c3cf60d861076bc40cf90bf26e66ad6f527"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:01.585265Z","signature_b64":"YIPv3D0Ev/DziQJnRvl6Akv5SX61i7EZJ3lMlkh3VJ1DzaEdzmmGG3ipwpVi2YZ9PjP//RF/pmfvAlEXa4rxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5272ab128696c98eb91e1ef449dddc9561ed867e9465c31b8b435378f3340a8","last_reissued_at":"2026-07-05T08:06:01.584806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:01.584806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bill Yuchen Lin, Graham Neubig, Junpeng Liu, Wai Lam, Xiang Yue, Yifan Song, Yuanzhi Li","submitted_at":"2024-04-09T02:29:39Z","abstract_excerpt":"Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed for general multimodal tasks, failing to capture the unique characteristics of web pages, or focus on end-to-end web agent tasks, unable to measure fine-grained abilities such as OCR, understanding, and grounding. In this paper, we introduce \\bench{}, a multimodal benchmark designed to assess the capabilities of MLLMs across a variety of web tasks. \\bench{} co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05955","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/2404.05955/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":"2404.05955","created_at":"2026-07-05T08:06:01.584864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05955v1","created_at":"2026-07-05T08:06:01.584864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05955","created_at":"2026-07-05T08:06:01.584864+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUTSVMJINFWJ","created_at":"2026-07-05T08:06:01.584864+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUTSVMJINFWJR24R","created_at":"2026-07-05T08:06:01.584864+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUTSVMJI","created_at":"2026-07-05T08:06:01.584864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06118","citing_title":"WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02032","citing_title":"PACE: A Proxy for Agentic Capability Evaluation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18048","citing_title":"DocOS: Towards Proactive Document-Guided Actions in GUI Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07062","citing_title":"Seed1.5-VL Technical Report","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF","json":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF.json","graph_json":"https://pith.science/api/pith-number/WUTSVMJINFWJR24R4HXUJHO5ZF/graph.json","events_json":"https://pith.science/api/pith-number/WUTSVMJINFWJR24R4HXUJHO5ZF/events.json","paper":"https://pith.science/paper/WUTSVMJI"},"agent_actions":{"view_html":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF","download_json":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF.json","view_paper":"https://pith.science/paper/WUTSVMJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05955&json=true","fetch_graph":"https://pith.science/api/pith-number/WUTSVMJINFWJR24R4HXUJHO5ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/WUTSVMJINFWJR24R4HXUJHO5ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF/action/storage_attestation","attest_author":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF/action/author_attestation","sign_citation":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF/action/citation_signature","submit_replication":"https://pith.science/pith/WUTSVMJINFWJR24R4HXUJHO5ZF/action/replication_record"}},"created_at":"2026-07-05T08:06:01.584864+00:00","updated_at":"2026-07-05T08:06:01.584864+00:00"}