{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FTS3ES6LIBR37E5FOHXTBNLCA6","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":"2cea0df84d0199853f197af33d4eb5e29b82c7c7a1405efa9f500f5a35158155","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-22T20:29:12Z","title_canon_sha256":"e2624a3836aab389d223536debbebe16cb58175e599651f59cad6e5eb98e58c2"},"schema_version":"1.0","source":{"id":"2605.26144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26144","created_at":"2026-05-27T00:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26144v1","created_at":"2026-05-27T00:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26144","created_at":"2026-05-27T00:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"FTS3ES6LIBR3","created_at":"2026-05-27T00:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"FTS3ES6LIBR37E5F","created_at":"2026-05-27T00:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"FTS3ES6L","created_at":"2026-05-27T00:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:a545e985ceb71b1e8d3dc5e4944a59cf78bafffa91380c22308a4baa914f95b1","target":"graph","created_at":"2026-05-27T00:04:26Z","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/2605.26144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with ","authors_text":"Jiawei (Joe) Zhou, Jingdi Chen, JunJia Guo, Yuhang Yao","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-22T20:29:12Z","title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26144","kind":"arxiv","version":1},"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":"sha256:4b1c1e31985c1a32269aa9c1fc78cfd67534ba5214b4d0a5abaea88981013c0e","target":"record","created_at":"2026-05-27T00:04:26Z","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":"2cea0df84d0199853f197af33d4eb5e29b82c7c7a1405efa9f500f5a35158155","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-22T20:29:12Z","title_canon_sha256":"e2624a3836aab389d223536debbebe16cb58175e599651f59cad6e5eb98e58c2"},"schema_version":"1.0","source":{"id":"2605.26144","kind":"arxiv","version":1}},"canonical_sha256":"2ce5b24bcb4063bf93a571ef30b56207be03e2ff23b52c1d392269d246945043","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ce5b24bcb4063bf93a571ef30b56207be03e2ff23b52c1d392269d246945043","first_computed_at":"2026-05-27T00:04:26.098008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T00:04:26.098008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"orSQsWsd+xbuvGdpVIxoZsmoJ/kYrdAqgoXINDONRMQWM3Z/jZQFyyeVyxWLew5ZS62kxlIcSzFy0D+wLxGVDA==","signature_status":"signed_v1","signed_at":"2026-05-27T00:04:26.098917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b1c1e31985c1a32269aa9c1fc78cfd67534ba5214b4d0a5abaea88981013c0e","sha256:a545e985ceb71b1e8d3dc5e4944a59cf78bafffa91380c22308a4baa914f95b1"],"state_sha256":"fe792ab295d4f286a82c336cb9db1b5664ccf9fa32d4b044031a07aa70515415"}