{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B32ZJSBWA45463QEUGJRWZCIJJ","short_pith_number":"pith:B32ZJSBW","schema_version":"1.0","canonical_sha256":"0ef594c836073bcf6e04a1931b64484a5615f1908025835324f1d88d6a92693f","source":{"kind":"arxiv","id":"2312.13108","version":2},"attestation_state":"computed","paper":{"title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difei Gao, Dongxing Mao, Hengxu Wang, Lei Ji, Luowei Zhou, Mike Zheng Shou, Mingyu Ouyang, Peiran Li, Peiyi Wang, Qinchen Wu, Weichen Zhang, Xiangwu Guo, Zechen Bai","submitted_at":"2023-12-20T15:28:38Z","abstract_excerpt":"Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown capabilities in automating tasks on Android and Web platforms. However, these tasks are primarily aimed at simple device usage and entertainment operations. This paper presents a novel benchmark, AssistGUI, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We carefully collected"},"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":"2312.13108","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T15:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"70595ed5e4bcdb372a46e755227cd7bdd928e8a0a4973a879722dbd5658c3501","abstract_canon_sha256":"ac1836e30cb246570b9b9a0a062fbdef2efc25634b2420b5995ff9e3adaea2fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:14.126054Z","signature_b64":"efB2imz7rVYeXdbYPpk/9toMted6wVfzFN/ZaYxfP7pljGysk9w8MnK31mIAaKALZaWnj2sL7tByhix6DHa0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ef594c836073bcf6e04a1931b64484a5615f1908025835324f1d88d6a92693f","last_reissued_at":"2026-07-05T07:29:14.125550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:14.125550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difei Gao, Dongxing Mao, Hengxu Wang, Lei Ji, Luowei Zhou, Mike Zheng Shou, Mingyu Ouyang, Peiran Li, Peiyi Wang, Qinchen Wu, Weichen Zhang, Xiangwu Guo, Zechen Bai","submitted_at":"2023-12-20T15:28:38Z","abstract_excerpt":"Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown capabilities in automating tasks on Android and Web platforms. However, these tasks are primarily aimed at simple device usage and entertainment operations. This paper presents a novel benchmark, AssistGUI, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We carefully collected"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13108","kind":"arxiv","version":2},"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/2312.13108/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":"2312.13108","created_at":"2026-07-05T07:29:14.125613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13108v2","created_at":"2026-07-05T07:29:14.125613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13108","created_at":"2026-07-05T07:29:14.125613+00:00"},{"alias_kind":"pith_short_12","alias_value":"B32ZJSBWA454","created_at":"2026-07-05T07:29:14.125613+00:00"},{"alias_kind":"pith_short_16","alias_value":"B32ZJSBWA45463QE","created_at":"2026-07-05T07:29:14.125613+00:00"},{"alias_kind":"pith_short_8","alias_value":"B32ZJSBW","created_at":"2026-07-05T07:29:14.125613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27761","citing_title":"AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications","ref_index":16,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07972","citing_title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07429","citing_title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ","json":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ.json","graph_json":"https://pith.science/api/pith-number/B32ZJSBWA45463QEUGJRWZCIJJ/graph.json","events_json":"https://pith.science/api/pith-number/B32ZJSBWA45463QEUGJRWZCIJJ/events.json","paper":"https://pith.science/paper/B32ZJSBW"},"agent_actions":{"view_html":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ","download_json":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ.json","view_paper":"https://pith.science/paper/B32ZJSBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13108&json=true","fetch_graph":"https://pith.science/api/pith-number/B32ZJSBWA45463QEUGJRWZCIJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/B32ZJSBWA45463QEUGJRWZCIJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ/action/storage_attestation","attest_author":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ/action/author_attestation","sign_citation":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ/action/citation_signature","submit_replication":"https://pith.science/pith/B32ZJSBWA45463QEUGJRWZCIJJ/action/replication_record"}},"created_at":"2026-07-05T07:29:14.125613+00:00","updated_at":"2026-07-05T07:29:14.125613+00:00"}