{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QARLB3NXO4E5GYBNL6LQIAXKRG","short_pith_number":"pith:QARLB3NX","schema_version":"1.0","canonical_sha256":"8022b0edb77709d3602d5f970402ea8990c35ef6f0587119feff77cf4322eecf","source":{"kind":"arxiv","id":"2506.14477","version":1},"attestation_state":"computed","paper":{"title":"GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Can Wang, Chun Chen, Jiawei Chen, Jingqi Yang, Linjun Sun, Mingli Song, Sheng Zhou, Xiaogang Ouyang, Zhilong Song","submitted_at":"2025-06-17T12:50:35Z","abstract_excerpt":"The development of high-quality datasets is crucial for benchmarking and advancing research in Graphical User Interface (GUI) agents. Despite their importance, existing datasets are often constructed under idealized conditions, overlooking the diverse anomalies frequently encountered in real-world deployments. To address this limitation, we introduce GUI-Robust, a novel dataset designed for comprehensive GUI agent evaluation, explicitly incorporating seven common types of anomalies observed in everyday GUI interactions. Furthermore, we propose a semi-automated dataset construction paradigm tha"},"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":"2506.14477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-17T12:50:35Z","cross_cats_sorted":[],"title_canon_sha256":"c60872cfd42591fd31b54d9cc823f4608e853bf595f903b05269dc3973d9dc06","abstract_canon_sha256":"17a4835a1876a3fe1e994549bbbec77dbff1c99b7cbba38358d7c74062adae6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:57.339670Z","signature_b64":"PpCnGxC7XB94oCcvkmjZcIkPw3qjdvchm/+99ZxhWN7bCd4MZDafosTAEFy5l4xhSsueyOVm/74CJaprkxDoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8022b0edb77709d3602d5f970402ea8990c35ef6f0587119feff77cf4322eecf","last_reissued_at":"2026-07-05T11:22:57.339162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:57.339162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Can Wang, Chun Chen, Jiawei Chen, Jingqi Yang, Linjun Sun, Mingli Song, Sheng Zhou, Xiaogang Ouyang, Zhilong Song","submitted_at":"2025-06-17T12:50:35Z","abstract_excerpt":"The development of high-quality datasets is crucial for benchmarking and advancing research in Graphical User Interface (GUI) agents. Despite their importance, existing datasets are often constructed under idealized conditions, overlooking the diverse anomalies frequently encountered in real-world deployments. To address this limitation, we introduce GUI-Robust, a novel dataset designed for comprehensive GUI agent evaluation, explicitly incorporating seven common types of anomalies observed in everyday GUI interactions. Furthermore, we propose a semi-automated dataset construction paradigm tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14477","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/2506.14477/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":"2506.14477","created_at":"2026-07-05T11:22:57.339221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14477v1","created_at":"2026-07-05T11:22:57.339221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14477","created_at":"2026-07-05T11:22:57.339221+00:00"},{"alias_kind":"pith_short_12","alias_value":"QARLB3NXO4E5","created_at":"2026-07-05T11:22:57.339221+00:00"},{"alias_kind":"pith_short_16","alias_value":"QARLB3NXO4E5GYBN","created_at":"2026-07-05T11:22:57.339221+00:00"},{"alias_kind":"pith_short_8","alias_value":"QARLB3NX","created_at":"2026-07-05T11:22:57.339221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.19679","citing_title":"InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25380","citing_title":"Benchmarking and Improving GUI Agents in High-Dynamic Environments","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24348","citing_title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23455","citing_title":"CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25380","citing_title":"Benchmarking and Improving GUI Agents in High-Dynamic Environments","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14262","citing_title":"GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG","json":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG.json","graph_json":"https://pith.science/api/pith-number/QARLB3NXO4E5GYBNL6LQIAXKRG/graph.json","events_json":"https://pith.science/api/pith-number/QARLB3NXO4E5GYBNL6LQIAXKRG/events.json","paper":"https://pith.science/paper/QARLB3NX"},"agent_actions":{"view_html":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG","download_json":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG.json","view_paper":"https://pith.science/paper/QARLB3NX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14477&json=true","fetch_graph":"https://pith.science/api/pith-number/QARLB3NXO4E5GYBNL6LQIAXKRG/graph.json","fetch_events":"https://pith.science/api/pith-number/QARLB3NXO4E5GYBNL6LQIAXKRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG/action/storage_attestation","attest_author":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG/action/author_attestation","sign_citation":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG/action/citation_signature","submit_replication":"https://pith.science/pith/QARLB3NXO4E5GYBNL6LQIAXKRG/action/replication_record"}},"created_at":"2026-07-05T11:22:57.339221+00:00","updated_at":"2026-07-05T11:22:57.339221+00:00"}