{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W5KX3T2PBDPYAFPO4LW7WPWEJM","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":"52bb5e45b6b03d713d6b02d88e04503611c1e60c20d4368abb59327fe84cc44a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T04:20:00Z","title_canon_sha256":"35578b2ae3efa4f9c8452933eb4eb81dba484ba204190715952c6fb8491ab814"},"schema_version":"1.0","source":{"id":"2508.20410","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20410","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20410v3","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20410","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"W5KX3T2PBDPY","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"W5KX3T2PBDPYAFPO","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"W5KX3T2P","created_at":"2026-07-05T12:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:d2eb57768f64f321141e1676cb31cdcee0199e75bf5dff6353e49211798b39e3","target":"graph","created_at":"2026-07-05T12:04:40Z","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/2508.20410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI text-to-app tools promise high quality applications and websites in minutes, yet no public benchmark rigorously verifies those claims. We introduce UI-Bench, the first large-scale benchmark that evaluates visual excellence across competing AI text-to-app tools through expert pairwise comparison. Spanning 10 tools, 30 prompts, 300 generated sites, and 4,000+ expert judgments, UI-Bench ranks systems with a TrueSkill-derived model that yields calibrated confidence intervals. UI-Bench establishes a reproducible standard for advancing AI-driven web design. We release (i) the complete prompt set,","authors_text":"Agustin Garcinuno, Sam Jung, Spencer Mateega","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T04:20:00Z","title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20410","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":"sha256:01ad8c61db816144490face61a188e29609e6823c903bcda1fc35b7d99b1042f","target":"record","created_at":"2026-07-05T12:04:40Z","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":"52bb5e45b6b03d713d6b02d88e04503611c1e60c20d4368abb59327fe84cc44a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T04:20:00Z","title_canon_sha256":"35578b2ae3efa4f9c8452933eb4eb81dba484ba204190715952c6fb8491ab814"},"schema_version":"1.0","source":{"id":"2508.20410","kind":"arxiv","version":3}},"canonical_sha256":"b7557dcf4f08df8015eee2edfb3ec44b0bffd23a907c61fd65155285e0a9d004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7557dcf4f08df8015eee2edfb3ec44b0bffd23a907c61fd65155285e0a9d004","first_computed_at":"2026-07-05T12:04:40.238484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:40.238484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2LuKDjJ5wMZe7sXLtkT9kOZ7kYb7o7xrAyjlkKaV+qkY+gp0xtpwa/wgJhg+79HCuHPyc8c6wiquQC4czZ5cBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:40.238986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20410","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01ad8c61db816144490face61a188e29609e6823c903bcda1fc35b7d99b1042f","sha256:d2eb57768f64f321141e1676cb31cdcee0199e75bf5dff6353e49211798b39e3"],"state_sha256":"a88a9a79db786a4ed5c7fed90bfeeb5bd7327bbcb6e9d00411381f8e6e189856"}