{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UGNRJGDSTGH5L3ZJHZZRCEO4TM","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":"1d1a05125b793f19e0a7e8d62f827d94ea03c3df741451f93435909ce2ac6cfd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T06:40:24Z","title_canon_sha256":"1e4a52be7415278169fcc20095b9c3379a6b893fab6114df1a18255a4e0571ce"},"schema_version":"1.0","source":{"id":"2605.29447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29447","created_at":"2026-05-29T01:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29447v1","created_at":"2026-05-29T01:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29447","created_at":"2026-05-29T01:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"UGNRJGDSTGH5","created_at":"2026-05-29T01:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"UGNRJGDSTGH5L3ZJ","created_at":"2026-05-29T01:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"UGNRJGDS","created_at":"2026-05-29T01:05:39Z"}],"graph_snapshots":[{"event_id":"sha256:658288f01f8dc25e9530b9e75094d2a6def3c6085466ed36ffc5ef6cbdffcfa2","target":"graph","created_at":"2026-05-29T01:05:39Z","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/2605.29447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation and data levels, we introduce GUI-RobustEval and propose Robustness-driven Trajectory Synthesis. GUI-RobustEval contains $1,216$ executable test cases that systematically measure error recovery capabilities across a broad and realistic spectrum of error modes. At the data level, RoTS is a scalable synthesis framework that creates $800k$ high-quality data via a tree-based pipeline that proactively discovers diverse er","authors_text":"Bin Yang, Hao Jiang, Hongtao Duan, Lu Jiang, Lulu Hu, Minying Zhang, Qihua Chen, Shurui Li, Tianpeng Bu, Xin Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T06:40:24Z","title":"Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29447","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":"sha256:6a2f3831993c847387bfcbcf60a64eef949b77b7f86e7452d2be801938351a71","target":"record","created_at":"2026-05-29T01:05:39Z","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":"1d1a05125b793f19e0a7e8d62f827d94ea03c3df741451f93435909ce2ac6cfd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T06:40:24Z","title_canon_sha256":"1e4a52be7415278169fcc20095b9c3379a6b893fab6114df1a18255a4e0571ce"},"schema_version":"1.0","source":{"id":"2605.29447","kind":"arxiv","version":1}},"canonical_sha256":"a19b149872998fd5ef293e731111dc9b27446dffa0b86f5828417497e2d1b3c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a19b149872998fd5ef293e731111dc9b27446dffa0b86f5828417497e2d1b3c3","first_computed_at":"2026-05-29T01:05:39.773755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:39.773755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TJAfRb+TUw2rJo9sCm8DJmf3msOuXgZV/HvZ+vy7+zyO1xYiCQmBB0C05/i4T3LCQjV6Tl6HorW2FUt9xKRCAg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:39.774598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a2f3831993c847387bfcbcf60a64eef949b77b7f86e7452d2be801938351a71","sha256:658288f01f8dc25e9530b9e75094d2a6def3c6085466ed36ffc5ef6cbdffcfa2"],"state_sha256":"45166163444dd4ed12a098416e19aa8386c27f0c58cbe8023057d032428df4e3"}