{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7RUUPOAIVNTKODNZABQRQ7N4RL","short_pith_number":"pith:7RUUPOAI","schema_version":"1.0","canonical_sha256":"fc6947b808ab66a70db90061187dbc8ada2565b9f2b082d587ee15500d85ec92","source":{"kind":"arxiv","id":"2603.26648","version":3},"attestation_state":"computed","paper":{"title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jie Tang, Mingdao Liu, Wenyi Hong, Xiaotao Gu, Zehai He, Zhen Yang, Ziyang Pan","submitted_at":"2026-03-27T17:50:45Z","abstract_excerpt":"Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, tho"},"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":"2603.26648","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-27T17:50:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58f4596dcb3607d68d3f5240a2b949b4840a9f3befa81c20adbba357b539937e","abstract_canon_sha256":"825ee39651250e316c3f86e4c3294d318216c26846623551b5f2f7f4d538f30e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:44.355199Z","signature_b64":"YWer8/pNTV+CvXXG5PFPUbFRJXyHNBhrZ37nBKNPwPkAZ80st2T2nAViMAt7Bk68vv9rxVbl48b9fPAcUK7eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6947b808ab66a70db90061187dbc8ada2565b9f2b082d587ee15500d85ec92","last_reissued_at":"2026-07-21T01:21:44.354213Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:44.354213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jie Tang, Mingdao Liu, Wenyi Hong, Xiaotao Gu, Zehai He, Zhen Yang, Ziyang Pan","submitted_at":"2026-03-27T17:50:45Z","abstract_excerpt":"Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, tho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26648","kind":"arxiv","version":3},"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/2603.26648/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":"2603.26648","created_at":"2026-07-21T01:21:44.354689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26648v3","created_at":"2026-07-21T01:21:44.354689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26648","created_at":"2026-07-21T01:21:44.354689+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RUUPOAIVNTK","created_at":"2026-07-21T01:21:44.354689+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RUUPOAIVNTKODNZ","created_at":"2026-07-21T01:21:44.354689+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RUUPOAI","created_at":"2026-07-21T01:21:44.354689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2607.06306","citing_title":"UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26807","citing_title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30000","citing_title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26752","citing_title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26752","citing_title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26752","citing_title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":135,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL","json":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL.json","graph_json":"https://pith.science/api/pith-number/7RUUPOAIVNTKODNZABQRQ7N4RL/graph.json","events_json":"https://pith.science/api/pith-number/7RUUPOAIVNTKODNZABQRQ7N4RL/events.json","paper":"https://pith.science/paper/7RUUPOAI"},"agent_actions":{"view_html":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL","download_json":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL.json","view_paper":"https://pith.science/paper/7RUUPOAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26648&json=true","fetch_graph":"https://pith.science/api/pith-number/7RUUPOAIVNTKODNZABQRQ7N4RL/graph.json","fetch_events":"https://pith.science/api/pith-number/7RUUPOAIVNTKODNZABQRQ7N4RL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL/action/storage_attestation","attest_author":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL/action/author_attestation","sign_citation":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL/action/citation_signature","submit_replication":"https://pith.science/pith/7RUUPOAIVNTKODNZABQRQ7N4RL/action/replication_record"}},"created_at":"2026-07-21T01:21:44.354689+00:00","updated_at":"2026-07-21T01:21:44.354689+00:00"}