{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YC435YHUQDQW23YCKVDUTZRRWR","short_pith_number":"pith:YC435YHU","schema_version":"1.0","canonical_sha256":"c0b9bee0f480e16d6f02554749e631b44c49c7afa5548d76cef4e675788a82ab","source":{"kind":"arxiv","id":"2403.02713","version":2},"attestation_state":"computed","paper":{"title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Duyu Tang, Jihao Wu, Jiwen Zhang, Minghui Liao, Nuo Xu, Xiao Xiao, Yihua Teng, Zhongyu Wei","submitted_at":"2024-03-05T07:09:35Z","abstract_excerpt":"Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual observations, existing studies typically consider little semantic information carried out by intermediate screenshots and screen operations. To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions shoul"},"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":"2403.02713","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T07:09:35Z","cross_cats_sorted":["cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"8578f46cb60bf0fbbe353091336b0fa4c1cf413f9bed46f4048bc82485c8d950","abstract_canon_sha256":"162e2f4f2c2b63726fe6f8143e59ec6236653d0539dd69f92d2baf758e10b567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:26.896010Z","signature_b64":"3/R08ibstcT1rZT5ej4J9IXSy52oZhrxz/VxtGack/D4wADgx2lYXVOf3H9jOp96aNMyST63fF0CMKxPhcYgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0b9bee0f480e16d6f02554749e631b44c49c7afa5548d76cef4e675788a82ab","last_reissued_at":"2026-07-05T08:43:26.895547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:26.895547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Duyu Tang, Jihao Wu, Jiwen Zhang, Minghui Liao, Nuo Xu, Xiao Xiao, Yihua Teng, Zhongyu Wei","submitted_at":"2024-03-05T07:09:35Z","abstract_excerpt":"Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual observations, existing studies typically consider little semantic information carried out by intermediate screenshots and screen operations. To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions shoul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02713","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/2403.02713/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":"2403.02713","created_at":"2026-07-05T08:43:26.895605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02713v2","created_at":"2026-07-05T08:43:26.895605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02713","created_at":"2026-07-05T08:43:26.895605+00:00"},{"alias_kind":"pith_short_12","alias_value":"YC435YHUQDQW","created_at":"2026-07-05T08:43:26.895605+00:00"},{"alias_kind":"pith_short_16","alias_value":"YC435YHUQDQW23YC","created_at":"2026-07-05T08:43:26.895605+00:00"},{"alias_kind":"pith_short_8","alias_value":"YC435YHU","created_at":"2026-07-05T08:43:26.895605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09373","citing_title":"LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04454","citing_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02345","citing_title":"UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20279","citing_title":"AgentLens: Adaptive Visual Modalities for Human-Agent Interaction in Mobile GUI Agents","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR","json":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR.json","graph_json":"https://pith.science/api/pith-number/YC435YHUQDQW23YCKVDUTZRRWR/graph.json","events_json":"https://pith.science/api/pith-number/YC435YHUQDQW23YCKVDUTZRRWR/events.json","paper":"https://pith.science/paper/YC435YHU"},"agent_actions":{"view_html":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR","download_json":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR.json","view_paper":"https://pith.science/paper/YC435YHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02713&json=true","fetch_graph":"https://pith.science/api/pith-number/YC435YHUQDQW23YCKVDUTZRRWR/graph.json","fetch_events":"https://pith.science/api/pith-number/YC435YHUQDQW23YCKVDUTZRRWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR/action/storage_attestation","attest_author":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR/action/author_attestation","sign_citation":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR/action/citation_signature","submit_replication":"https://pith.science/pith/YC435YHUQDQW23YCKVDUTZRRWR/action/replication_record"}},"created_at":"2026-07-05T08:43:26.895605+00:00","updated_at":"2026-07-05T08:43:26.895605+00:00"}