{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MGO6YUUCWYNQR5RM435GDUI7EC","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":"cdc9e437ddf58b31bf75fa6b7eab1cc3c85fc351bb2c025ad278f6ca7a4215d4","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T05:30:22Z","title_canon_sha256":"cc9de8b9249206849d7ba3eb8a38f07b2e7791035e9f96212e6655c43d03ce82"},"schema_version":"1.0","source":{"id":"2503.03196","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03196","created_at":"2026-07-05T10:49:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03196v2","created_at":"2026-07-05T10:49:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03196","created_at":"2026-07-05T10:49:51Z"},{"alias_kind":"pith_short_12","alias_value":"MGO6YUUCWYNQ","created_at":"2026-07-05T10:49:51Z"},{"alias_kind":"pith_short_16","alias_value":"MGO6YUUCWYNQR5RM","created_at":"2026-07-05T10:49:51Z"},{"alias_kind":"pith_short_8","alias_value":"MGO6YUUC","created_at":"2026-07-05T10:49:51Z"}],"graph_snapshots":[{"event_id":"sha256:553a85a75a3a6d3b6ac559424178192011dcd12aae9d153f3ae6bfa3909c368b","target":"graph","created_at":"2026-07-05T10:49:51Z","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/2503.03196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphical User Interface (GUI) agents show amazing abilities in assisting human-computer interaction, automating human user's navigation on digital devices. An ideal GUI agent is expected to achieve high accuracy, low latency, and compatibility for different GUI platforms. Recent vision-based approaches have shown promise by leveraging advanced Vision Language Models (VLMs). While they generally meet the requirements of compatibility and low latency, these vision-based GUI agents tend to have low accuracy due to their limitations in element grounding. To address this issue, we propose $\\textbf","authors_text":"Junting Pan, Mingjie Zhan, Zhaohui Hou, Zhiyuan Huang, Ziming Cheng","cross_cats":["cs.HC","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T05:30:22Z","title":"SpiritSight Agent: Advanced GUI Agent with One Look"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03196","kind":"arxiv","version":2},"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":"sha256:40e67e319fa57b3efefb8a018e57212103868661244c0f65750db81add6d187a","target":"record","created_at":"2026-07-05T10:49:51Z","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":"cdc9e437ddf58b31bf75fa6b7eab1cc3c85fc351bb2c025ad278f6ca7a4215d4","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T05:30:22Z","title_canon_sha256":"cc9de8b9249206849d7ba3eb8a38f07b2e7791035e9f96212e6655c43d03ce82"},"schema_version":"1.0","source":{"id":"2503.03196","kind":"arxiv","version":2}},"canonical_sha256":"619dec5282b61b08f62ce6fa61d11f20a43a8eb7daa0531ee065f060372e7898","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"619dec5282b61b08f62ce6fa61d11f20a43a8eb7daa0531ee065f060372e7898","first_computed_at":"2026-07-05T10:49:51.979010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:51.979010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rCIq5UZy90wKZ7X1UDXxsyINRhwFk6veQ7TsOX3fxfgTnOfMHQKeC5sEx8KRpuRaUZqKHiAZqwsHxPnb4uhxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:51.979497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03196","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40e67e319fa57b3efefb8a018e57212103868661244c0f65750db81add6d187a","sha256:553a85a75a3a6d3b6ac559424178192011dcd12aae9d153f3ae6bfa3909c368b"],"state_sha256":"9a9e4723377174e80743716b5d6d20104b2dffd83276a67792f08a158f935ae7"}