{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7RUUPOAIVNTKODNZABQRQ7N4RL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"825ee39651250e316c3f86e4c3294d318216c26846623551b5f2f7f4d538f30e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-27T17:50:45Z","title_canon_sha256":"58f4596dcb3607d68d3f5240a2b949b4840a9f3befa81c20adbba357b539937e"},"schema_version":"1.0","source":{"id":"2603.26648","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.26648","created_at":"2026-07-21T01:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.26648v3","created_at":"2026-07-21T01:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26648","created_at":"2026-07-21T01:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"7RUUPOAIVNTK","created_at":"2026-07-21T01:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"7RUUPOAIVNTKODNZ","created_at":"2026-07-21T01:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"7RUUPOAI","created_at":"2026-07-21T01:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:6d63d229dd7956b73d746851ffba2aba361841806d1db7fedf81cfc1409c1d9b","target":"graph","created_at":"2026-07-21T01:21:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.26648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jie Tang, Mingdao Liu, Wenyi Hong, Xiaotao Gu, Zehai He, Zhen Yang, Ziyang Pan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-27T17:50:45Z","title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26648","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c871f4ac9baa150b42af27f42afef0371cef4b1f7ce7ceadf387edc70065b68","target":"record","created_at":"2026-07-21T01:21:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"825ee39651250e316c3f86e4c3294d318216c26846623551b5f2f7f4d538f30e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-27T17:50:45Z","title_canon_sha256":"58f4596dcb3607d68d3f5240a2b949b4840a9f3befa81c20adbba357b539937e"},"schema_version":"1.0","source":{"id":"2603.26648","kind":"arxiv","version":3}},"canonical_sha256":"fc6947b808ab66a70db90061187dbc8ada2565b9f2b082d587ee15500d85ec92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc6947b808ab66a70db90061187dbc8ada2565b9f2b082d587ee15500d85ec92","first_computed_at":"2026-07-21T01:21:44.354213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:44.354213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YWer8/pNTV+CvXXG5PFPUbFRJXyHNBhrZ37nBKNPwPkAZ80st2T2nAViMAt7Bk68vv9rxVbl48b9fPAcUK7eCQ==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:44.355199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.26648","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c871f4ac9baa150b42af27f42afef0371cef4b1f7ce7ceadf387edc70065b68","sha256:6d63d229dd7956b73d746851ffba2aba361841806d1db7fedf81cfc1409c1d9b"],"state_sha256":"d115f8da92d0c6c53b28523753bbdfae1899be04c48b2041b0ec139ff22503bf"}