{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MI37PUJDHGPLYWPKMUFNLO4PIK","short_pith_number":"pith:MI37PUJD","schema_version":"1.0","canonical_sha256":"6237f7d123399ebc59ea650ad5bb8f42b0930dcccda5f03d7563a3a7e1b9d52b","source":{"kind":"arxiv","id":"2411.17465","version":1},"attestation_state":"computed","paper":{"title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Difei Gao, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Shiwei Wu, Weixian Lei, Zechen Bai, Zhengyuan Yang","submitted_at":"2024-11-26T14:29:47Z","abstract_excerpt":"Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI conne"},"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":"2411.17465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:29:47Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"0ce4ec50948896567c7eadf5d361622c4c52639baf8f778b45c8bd997a24c12f","abstract_canon_sha256":"bbc7f12fbc3c6e9bfe0c8b4474f2cfe92f85c3c47fee3ef7e78224af30a76854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:47.575440Z","signature_b64":"aYSmVkqUg2gFMDD4M3PRUil5a5y5Q5o01PG82/fzSZZqw3+Up9cCLbDrUGMivdTw5VeKsHJTjtAtTvyc8wYGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6237f7d123399ebc59ea650ad5bb8f42b0930dcccda5f03d7563a3a7e1b9d52b","last_reissued_at":"2026-07-05T09:40:47.575024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:47.575024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Difei Gao, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Shiwei Wu, Weixian Lei, Zechen Bai, Zhengyuan Yang","submitted_at":"2024-11-26T14:29:47Z","abstract_excerpt":"Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI conne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17465","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/2411.17465/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":"2411.17465","created_at":"2026-07-05T09:40:47.575088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17465v1","created_at":"2026-07-05T09:40:47.575088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17465","created_at":"2026-07-05T09:40:47.575088+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI37PUJDHGPL","created_at":"2026-07-05T09:40:47.575088+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI37PUJDHGPLYWPK","created_at":"2026-07-05T09:40:47.575088+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI37PUJD","created_at":"2026-07-05T09:40:47.575088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06560","citing_title":"Vision as Unified Multimodal Generation","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29537","citing_title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30884","citing_title":"GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2505.10887","citing_title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16565","citing_title":"Skim: Speculative Execution for Fast and Efficient Web Agents","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22102","citing_title":"Mitigating Coordinate Prediction Bias from Positional Encoding Failures","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14113","citing_title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21375","citing_title":"VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK","json":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK.json","graph_json":"https://pith.science/api/pith-number/MI37PUJDHGPLYWPKMUFNLO4PIK/graph.json","events_json":"https://pith.science/api/pith-number/MI37PUJDHGPLYWPKMUFNLO4PIK/events.json","paper":"https://pith.science/paper/MI37PUJD"},"agent_actions":{"view_html":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK","download_json":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK.json","view_paper":"https://pith.science/paper/MI37PUJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17465&json=true","fetch_graph":"https://pith.science/api/pith-number/MI37PUJDHGPLYWPKMUFNLO4PIK/graph.json","fetch_events":"https://pith.science/api/pith-number/MI37PUJDHGPLYWPKMUFNLO4PIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK/action/storage_attestation","attest_author":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK/action/author_attestation","sign_citation":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK/action/citation_signature","submit_replication":"https://pith.science/pith/MI37PUJDHGPLYWPKMUFNLO4PIK/action/replication_record"}},"created_at":"2026-07-05T09:40:47.575088+00:00","updated_at":"2026-07-05T09:40:47.575088+00:00"}