{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W5KX3T2PBDPYAFPO4LW7WPWEJM","short_pith_number":"pith:W5KX3T2P","schema_version":"1.0","canonical_sha256":"b7557dcf4f08df8015eee2edfb3ec44b0bffd23a907c61fd65155285e0a9d004","source":{"kind":"arxiv","id":"2508.20410","version":3},"attestation_state":"computed","paper":{"title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agustin Garcinuno, Sam Jung, Spencer Mateega","submitted_at":"2025-08-28T04:20:00Z","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,"},"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":"2508.20410","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T04:20:00Z","cross_cats_sorted":[],"title_canon_sha256":"35578b2ae3efa4f9c8452933eb4eb81dba484ba204190715952c6fb8491ab814","abstract_canon_sha256":"52bb5e45b6b03d713d6b02d88e04503611c1e60c20d4368abb59327fe84cc44a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:40.238986Z","signature_b64":"2LuKDjJ5wMZe7sXLtkT9kOZ7kYb7o7xrAyjlkKaV+qkY+gp0xtpwa/wgJhg+79HCuHPyc8c6wiquQC4czZ5cBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7557dcf4f08df8015eee2edfb3ec44b0bffd23a907c61fd65155285e0a9d004","last_reissued_at":"2026-07-05T12:04:40.238484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:40.238484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agustin Garcinuno, Sam Jung, Spencer Mateega","submitted_at":"2025-08-28T04:20:00Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20410","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/2508.20410/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":"2508.20410","created_at":"2026-07-05T12:04:40.238543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20410v3","created_at":"2026-07-05T12:04:40.238543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20410","created_at":"2026-07-05T12:04:40.238543+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5KX3T2PBDPY","created_at":"2026-07-05T12:04:40.238543+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5KX3T2PBDPYAFPO","created_at":"2026-07-05T12:04:40.238543+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5KX3T2P","created_at":"2026-07-05T12:04:40.238543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30000","citing_title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM","json":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM.json","graph_json":"https://pith.science/api/pith-number/W5KX3T2PBDPYAFPO4LW7WPWEJM/graph.json","events_json":"https://pith.science/api/pith-number/W5KX3T2PBDPYAFPO4LW7WPWEJM/events.json","paper":"https://pith.science/paper/W5KX3T2P"},"agent_actions":{"view_html":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM","download_json":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM.json","view_paper":"https://pith.science/paper/W5KX3T2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20410&json=true","fetch_graph":"https://pith.science/api/pith-number/W5KX3T2PBDPYAFPO4LW7WPWEJM/graph.json","fetch_events":"https://pith.science/api/pith-number/W5KX3T2PBDPYAFPO4LW7WPWEJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM/action/storage_attestation","attest_author":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM/action/author_attestation","sign_citation":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM/action/citation_signature","submit_replication":"https://pith.science/pith/W5KX3T2PBDPYAFPO4LW7WPWEJM/action/replication_record"}},"created_at":"2026-07-05T12:04:40.238543+00:00","updated_at":"2026-07-05T12:04:40.238543+00:00"}