{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F6QQXLNSBYW76BT4FPTN6S4B25","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":"b353ab0b1b0dc8030c2d0ab798403bfaac00bcf955f26d9327a09a678bb02b78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T02:48:52Z","title_canon_sha256":"0c42e8468ecdb73cd34c549002f5bb912b008e7ae1497e82acb7242d099f0cc5"},"schema_version":"1.0","source":{"id":"2605.16402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16402","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16402v1","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16402","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"F6QQXLNSBYW7","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"F6QQXLNSBYW76BT4","created_at":"2026-05-20T00:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"F6QQXLNS","created_at":"2026-05-20T00:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:122185936281eb487c22aaf589b25aaeca8b0e44094e43394910806ecef98254","target":"graph","created_at":"2026-05-20T00:02:20Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T20:41:57.241956Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.601745Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16402/integrity.json","findings":[],"snapshot_sha256":"b7612c26955cfccf01e195bb65e64dc8c194f9c520fdf2ba951797b4f23093d0","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have revolutionized GUI automation, yet their efficacy is largely established on idealized, single-layer interfaces. This paper identifies a critical reliability gap: state-of-the-art agents face distinct robustness challenges in real-world desktop environments characterized by multi-window stacking, occlusion, and visual clutter. To address this, we introduce WinDeskGround, a novel benchmark and synthesis framework tailored for evaluating GUI grounding robustness. Unlike static datasets, our framework parametrically generates complex desktop scenarios ","authors_text":"Haoren Zhao, Tianyi Chen, Zhen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T02:48:52Z","title":"WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16402","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":"sha256:87b0aafaa8fb3f355fbb8bedcc4e3d37b7d1e6728f458e751642b2b58cef4e61","target":"record","created_at":"2026-05-20T00:02:20Z","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":"b353ab0b1b0dc8030c2d0ab798403bfaac00bcf955f26d9327a09a678bb02b78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T02:48:52Z","title_canon_sha256":"0c42e8468ecdb73cd34c549002f5bb912b008e7ae1497e82acb7242d099f0cc5"},"schema_version":"1.0","source":{"id":"2605.16402","kind":"arxiv","version":1}},"canonical_sha256":"2fa10badb20e2dff067c2be6df4b81d7654427e64b6267a9fe3ed9b83ed649e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fa10badb20e2dff067c2be6df4b81d7654427e64b6267a9fe3ed9b83ed649e1","first_computed_at":"2026-05-20T00:02:20.489877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:20.489877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HZg/8kay/IMFWZ6CDCKr/W/z6tMuF/Fy7jSxODgPzSSgfHYEu043Qfeo/aDRb+mC2FGoyMMrmOpj4i+1BNnrDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:20.491486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87b0aafaa8fb3f355fbb8bedcc4e3d37b7d1e6728f458e751642b2b58cef4e61","sha256:122185936281eb487c22aaf589b25aaeca8b0e44094e43394910806ecef98254"],"state_sha256":"2bef299aa40eb11b234ad1cf10d93c8a2740a4a9e24fbb2271df43a1f346c089"}