{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6H7EWJ7HGGKONCREQADNKFEWNN","short_pith_number":"pith:6H7EWJ7H","schema_version":"1.0","canonical_sha256":"f1fe4b27e73194e68a248006d514966b6d4831942d7f830efbe0fa87de0b94f8","source":{"kind":"arxiv","id":"2606.05697","version":1},"attestation_state":"computed","paper":{"title":"PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gian Maria Marconi, Narimasa Watanabe, Nicolas Bougie, Xiaotong Ye","submitted_at":"2026-06-04T04:35:16Z","abstract_excerpt":"User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly. In light of this, recent work has explored Multimodal Large Language Models as proxy evaluators. However, existing approaches either produce surface-level critiques or a judgment that reflects the model's own biases rather than the genuine response of a particular user. We introduce PerceptUI, a framework for persona-conditioned UI/UX evaluation that predicts how "},"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":"2606.05697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T04:35:16Z","cross_cats_sorted":[],"title_canon_sha256":"a31a666c5f87aeb3998c893f901934e006eb25c140a21e5d858268f46a63922e","abstract_canon_sha256":"c5c4ebd54faf7aaba906a0fa69a6e803573b12487504f11c0c490474232c7616"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:59.586389Z","signature_b64":"5ZBY8fQbAfyxRYIKJVFKvZtGhDCbx3Wilp55dOg2oZFFHabZ4yxkoX5OfAvMF6OwB0LlVRVkKiVfyNx4V46ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1fe4b27e73194e68a248006d514966b6d4831942d7f830efbe0fa87de0b94f8","last_reissued_at":"2026-06-05T01:14:59.585916Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:59.585916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gian Maria Marconi, Narimasa Watanabe, Nicolas Bougie, Xiaotong Ye","submitted_at":"2026-06-04T04:35:16Z","abstract_excerpt":"User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly. In light of this, recent work has explored Multimodal Large Language Models as proxy evaluators. However, existing approaches either produce surface-level critiques or a judgment that reflects the model's own biases rather than the genuine response of a particular user. We introduce PerceptUI, a framework for persona-conditioned UI/UX evaluation that predicts how "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05697","kind":"arxiv","version":1},"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/2606.05697/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":"2606.05697","created_at":"2026-06-05T01:14:59.585989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05697v1","created_at":"2026-06-05T01:14:59.585989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05697","created_at":"2026-06-05T01:14:59.585989+00:00"},{"alias_kind":"pith_short_12","alias_value":"6H7EWJ7HGGKO","created_at":"2026-06-05T01:14:59.585989+00:00"},{"alias_kind":"pith_short_16","alias_value":"6H7EWJ7HGGKONCRE","created_at":"2026-06-05T01:14:59.585989+00:00"},{"alias_kind":"pith_short_8","alias_value":"6H7EWJ7H","created_at":"2026-06-05T01:14:59.585989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN","json":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN.json","graph_json":"https://pith.science/api/pith-number/6H7EWJ7HGGKONCREQADNKFEWNN/graph.json","events_json":"https://pith.science/api/pith-number/6H7EWJ7HGGKONCREQADNKFEWNN/events.json","paper":"https://pith.science/paper/6H7EWJ7H"},"agent_actions":{"view_html":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN","download_json":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN.json","view_paper":"https://pith.science/paper/6H7EWJ7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05697&json=true","fetch_graph":"https://pith.science/api/pith-number/6H7EWJ7HGGKONCREQADNKFEWNN/graph.json","fetch_events":"https://pith.science/api/pith-number/6H7EWJ7HGGKONCREQADNKFEWNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN/action/storage_attestation","attest_author":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN/action/author_attestation","sign_citation":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN/action/citation_signature","submit_replication":"https://pith.science/pith/6H7EWJ7HGGKONCREQADNKFEWNN/action/replication_record"}},"created_at":"2026-06-05T01:14:59.585989+00:00","updated_at":"2026-06-05T01:14:59.585989+00:00"}