{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VGY7IERMDRGA2DKCFLVGSTTX66","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":"714c2d3122fef6d8c3be15543a4ba15bcc150e66af07384b025fb3beeb23d16e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T00:00:43Z","title_canon_sha256":"22d2e2f06214c3b0a41dcf40867e2f4b6f0c895e0832f60b7fe26c21cfe04d98"},"schema_version":"1.0","source":{"id":"2408.00203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00203","created_at":"2026-07-05T08:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00203v1","created_at":"2026-07-05T08:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00203","created_at":"2026-07-05T08:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"VGY7IERMDRGA","created_at":"2026-07-05T08:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"VGY7IERMDRGA2DKC","created_at":"2026-07-05T08:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"VGY7IERM","created_at":"2026-07-05T08:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:3b30e7cb725947dda2d44fb8ee776b7dcf69d3d7ccfd98ffbd9992ae56127974","target":"graph","created_at":"2026-07-05T08:50:59Z","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/2408.00203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of large vision language models shows great potential in driving the agent system operating on user interfaces. However, we argue that the power multimodal models like GPT-4V as a general agent on multiple operating systems across different applications is largely underestimated due to the lack of a robust screen parsing technique capable of: 1) reliably identifying interactable icons within the user interface, and 2) understanding the semantics of various elements in a screenshot and accurately associate the intended action with the corresponding region on the screen. To fi","authors_text":"Ahmed Awadallah, Jianwei Yang, Yadong Lu, Yelong Shen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T00:00:43Z","title":"OmniParser for Pure Vision Based GUI Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00203","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":"sha256:28418ae3b0a764d9ca81110b4b53c39b332bc0e1e3caf0656c87b4fbc9171716","target":"record","created_at":"2026-07-05T08:50:59Z","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":"714c2d3122fef6d8c3be15543a4ba15bcc150e66af07384b025fb3beeb23d16e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T00:00:43Z","title_canon_sha256":"22d2e2f06214c3b0a41dcf40867e2f4b6f0c895e0832f60b7fe26c21cfe04d98"},"schema_version":"1.0","source":{"id":"2408.00203","kind":"arxiv","version":1}},"canonical_sha256":"a9b1f4122c1c4c0d0d422aea694e77f78a68bb5f7693ec342177930fa1a765e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9b1f4122c1c4c0d0d422aea694e77f78a68bb5f7693ec342177930fa1a765e2","first_computed_at":"2026-07-05T08:50:59.966184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:59.966184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bG2b76vU1SDVj/MZ69A9PUFQlyM5lGK7VwqHBJZ0jgwZ2pSi7f1eOkP3DOhVmwZynZ9cCq2rSfXXyn4Q94x/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:59.966601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28418ae3b0a764d9ca81110b4b53c39b332bc0e1e3caf0656c87b4fbc9171716","sha256:3b30e7cb725947dda2d44fb8ee776b7dcf69d3d7ccfd98ffbd9992ae56127974"],"state_sha256":"a95f82f3a4e84489b8233075aa36bd70dc3b63a7abea6934e35d92cffb5f3198"}