{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:346VHMT3PX27352I2MBV3SSLM6","short_pith_number":"pith:346VHMT3","schema_version":"1.0","canonical_sha256":"df3d53b27b7df5fdf748d3035dca4b679134320dc96fe5022127bf646a9b7b2e","source":{"kind":"arxiv","id":"2304.07061","version":5},"attestation_state":"computed","paper":{"title":"DroidBot-GPT: GPT-powered UI Automation for Android","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hao Wen, Hongming Wang, Jiaxuan Liu, Yuanchun Li","submitted_at":"2023-04-14T11:31:56Z","abstract_excerpt":"This paper introduces DroidBot-GPT, a tool that utilizes GPT-like large language models (LLMs) to automate the interactions with Android mobile applications. Given a natural language description of a desired task, DroidBot-GPT can automatically generate and execute actions that navigate the app to complete the task. It works by translating the app GUI state information and the available actions on the smartphone screen to natural language prompts and asking the LLM to make a choice of actions. Since the LLM is typically trained on a large amount of data including the how-to manuals of diverse "},"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":"2304.07061","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-04-14T11:31:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebcac26ecd08a5e81db8fe4debc799f4a9b46d4bcb320bbc17539d5a9536d6fa","abstract_canon_sha256":"deb7d178b034d90c9aeb3e9ad749764e8b118b708d3d7b581ca5867368f70f9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:48.222212Z","signature_b64":"wXqJW+Tb0EaNKHweDYHrSqn4RIVrts3+asSJ4QOzeei7YgGt2xRjKMfhbzA8i/ap1KplXPpD+aBXTAucAd7yBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df3d53b27b7df5fdf748d3035dca4b679134320dc96fe5022127bf646a9b7b2e","last_reissued_at":"2026-07-05T07:30:48.221767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:48.221767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DroidBot-GPT: GPT-powered UI Automation for Android","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hao Wen, Hongming Wang, Jiaxuan Liu, Yuanchun Li","submitted_at":"2023-04-14T11:31:56Z","abstract_excerpt":"This paper introduces DroidBot-GPT, a tool that utilizes GPT-like large language models (LLMs) to automate the interactions with Android mobile applications. Given a natural language description of a desired task, DroidBot-GPT can automatically generate and execute actions that navigate the app to complete the task. It works by translating the app GUI state information and the available actions on the smartphone screen to natural language prompts and asking the LLM to make a choice of actions. Since the LLM is typically trained on a large amount of data including the how-to manuals of diverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07061","kind":"arxiv","version":5},"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/2304.07061/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":"2304.07061","created_at":"2026-07-05T07:30:48.221825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07061v5","created_at":"2026-07-05T07:30:48.221825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07061","created_at":"2026-07-05T07:30:48.221825+00:00"},{"alias_kind":"pith_short_12","alias_value":"346VHMT3PX27","created_at":"2026-07-05T07:30:48.221825+00:00"},{"alias_kind":"pith_short_16","alias_value":"346VHMT3PX27352I","created_at":"2026-07-05T07:30:48.221825+00:00"},{"alias_kind":"pith_short_8","alias_value":"346VHMT3","created_at":"2026-07-05T07:30:48.221825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11069","citing_title":"A survey on factors influencing mobile application usability through the lens of PACMAD+3 model","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02977","citing_title":"Large Language Model-Based Agents for Software Engineering: A Survey","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00458","citing_title":"LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10661","citing_title":"DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13463","citing_title":"From Exploration to Specification: LLM-Based Property Generation for Mobile App Testing","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14872","citing_title":"SkillDroid: Compile Once, Reuse Forever","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17817","citing_title":"Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19081","citing_title":"Proactive Detection of GUI Defects in Multi-Window Scenarios via Multimodal Reasoning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6","json":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6.json","graph_json":"https://pith.science/api/pith-number/346VHMT3PX27352I2MBV3SSLM6/graph.json","events_json":"https://pith.science/api/pith-number/346VHMT3PX27352I2MBV3SSLM6/events.json","paper":"https://pith.science/paper/346VHMT3"},"agent_actions":{"view_html":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6","download_json":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6.json","view_paper":"https://pith.science/paper/346VHMT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07061&json=true","fetch_graph":"https://pith.science/api/pith-number/346VHMT3PX27352I2MBV3SSLM6/graph.json","fetch_events":"https://pith.science/api/pith-number/346VHMT3PX27352I2MBV3SSLM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6/action/storage_attestation","attest_author":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6/action/author_attestation","sign_citation":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6/action/citation_signature","submit_replication":"https://pith.science/pith/346VHMT3PX27352I2MBV3SSLM6/action/replication_record"}},"created_at":"2026-07-05T07:30:48.221825+00:00","updated_at":"2026-07-05T07:30:48.221825+00:00"}