{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VGY7IERMDRGA2DKCFLVGSTTX66","short_pith_number":"pith:VGY7IERM","schema_version":"1.0","canonical_sha256":"a9b1f4122c1c4c0d0d422aea694e77f78a68bb5f7693ec342177930fa1a765e2","source":{"kind":"arxiv","id":"2408.00203","version":1},"attestation_state":"computed","paper":{"title":"OmniParser for Pure Vision Based GUI Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmed Awadallah, Jianwei Yang, Yadong Lu, Yelong Shen","submitted_at":"2024-08-01T00:00:43Z","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"},"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":"2408.00203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T00:00:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"22d2e2f06214c3b0a41dcf40867e2f4b6f0c895e0832f60b7fe26c21cfe04d98","abstract_canon_sha256":"714c2d3122fef6d8c3be15543a4ba15bcc150e66af07384b025fb3beeb23d16e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:59.966601Z","signature_b64":"bG2b76vU1SDVj/MZ69A9PUFQlyM5lGK7VwqHBJZ0jgwZ2pSi7f1eOkP3DOhVmwZynZ9cCq2rSfXXyn4Q94x/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b1f4122c1c4c0d0d422aea694e77f78a68bb5f7693ec342177930fa1a765e2","last_reissued_at":"2026-07-05T08:50:59.966184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:59.966184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniParser for Pure Vision Based GUI Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmed Awadallah, Jianwei Yang, Yadong Lu, Yelong Shen","submitted_at":"2024-08-01T00:00:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00203","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/2408.00203/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":"2408.00203","created_at":"2026-07-05T08:50:59.966236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00203v1","created_at":"2026-07-05T08:50:59.966236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00203","created_at":"2026-07-05T08:50:59.966236+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGY7IERMDRGA","created_at":"2026-07-05T08:50:59.966236+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGY7IERMDRGA2DKC","created_at":"2026-07-05T08:50:59.966236+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGY7IERM","created_at":"2026-07-05T08:50:59.966236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12666","citing_title":"CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10522","citing_title":"GUI-AC: Enhancing Continual Learning in GUI Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14923","citing_title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29705","citing_title":"GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16042","citing_title":"OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19260","citing_title":"AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15542","citing_title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2509.09505","citing_title":"Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21816","citing_title":"From Task to Tutorial: An Automated GUI Framework for Excel Tutorial Document and Video Creation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04454","citing_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05791","citing_title":"GTA1: GUI Test-time Scaling Agent","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18842","citing_title":"GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11724","citing_title":"WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28001","citing_title":"A Pattern Language for Resilient Visual Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06664","citing_title":"BAMI: Training-Free Bias Mitigation in GUI Grounding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08516","citing_title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66","json":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66.json","graph_json":"https://pith.science/api/pith-number/VGY7IERMDRGA2DKCFLVGSTTX66/graph.json","events_json":"https://pith.science/api/pith-number/VGY7IERMDRGA2DKCFLVGSTTX66/events.json","paper":"https://pith.science/paper/VGY7IERM"},"agent_actions":{"view_html":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66","download_json":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66.json","view_paper":"https://pith.science/paper/VGY7IERM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00203&json=true","fetch_graph":"https://pith.science/api/pith-number/VGY7IERMDRGA2DKCFLVGSTTX66/graph.json","fetch_events":"https://pith.science/api/pith-number/VGY7IERMDRGA2DKCFLVGSTTX66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66/action/storage_attestation","attest_author":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66/action/author_attestation","sign_citation":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66/action/citation_signature","submit_replication":"https://pith.science/pith/VGY7IERMDRGA2DKCFLVGSTTX66/action/replication_record"}},"created_at":"2026-07-05T08:50:59.966236+00:00","updated_at":"2026-07-05T08:50:59.966236+00:00"}