{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FUJQZB3OP4BRT3N6EWBW47PVH7","short_pith_number":"pith:FUJQZB3O","schema_version":"1.0","canonical_sha256":"2d130c876e7f0319edbe25836e7df53fc14cdf27aeefbaf98cc820242bf8a14a","source":{"kind":"arxiv","id":"2410.24024","version":2},"attestation_state":"computed","paper":{"title":"AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dan Zhang, Hanyu Lai, Hao Yu, Jie Tang, Shudan Zhang, Siyi Cheng, Xiao Liu, Xueqiao Sun, Yifan Xu, Yuxiao Dong","submitted_at":"2024-10-31T15:25:20Z","abstract_excerpt":"Autonomous agents have become increasingly important for interacting with the real world. Android agents, in particular, have been recently a frequently-mentioned interaction method. However, existing studies for training and evaluating Android agents lack systematic research on both open-source and closed-source models. In this work, we propose AndroidLab as a systematic Android agent framework. It includes an operation environment with different modalities, action space, and a reproducible benchmark. It supports both large language models (LLMs) and multimodal models (LMMs) in the same actio"},"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":"2410.24024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T15:25:20Z","cross_cats_sorted":[],"title_canon_sha256":"c16d033ffe873df6088f79fc7a30df1f40158a643148003745fe7430bdcb4144","abstract_canon_sha256":"0c0643ab0f641d6954fa83ab51ab9ef0e5d5aecb36020ade5263f893bfd8e41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:24.130208Z","signature_b64":"TUDIGI7l42Vl3ad4W1QVhvViNa2TIGI+M7YTyHrwC75dkl5Zzb17NtctOH/X1koH0tBH5g7qteAi95ADp20/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d130c876e7f0319edbe25836e7df53fc14cdf27aeefbaf98cc820242bf8a14a","last_reissued_at":"2026-07-05T09:30:24.129721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:24.129721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dan Zhang, Hanyu Lai, Hao Yu, Jie Tang, Shudan Zhang, Siyi Cheng, Xiao Liu, Xueqiao Sun, Yifan Xu, Yuxiao Dong","submitted_at":"2024-10-31T15:25:20Z","abstract_excerpt":"Autonomous agents have become increasingly important for interacting with the real world. Android agents, in particular, have been recently a frequently-mentioned interaction method. However, existing studies for training and evaluating Android agents lack systematic research on both open-source and closed-source models. In this work, we propose AndroidLab as a systematic Android agent framework. It includes an operation environment with different modalities, action space, and a reproducible benchmark. It supports both large language models (LLMs) and multimodal models (LMMs) in the same actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24024","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/2410.24024/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":"2410.24024","created_at":"2026-07-05T09:30:24.129787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24024v2","created_at":"2026-07-05T09:30:24.129787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24024","created_at":"2026-07-05T09:30:24.129787+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUJQZB3OP4BR","created_at":"2026-07-05T09:30:24.129787+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUJQZB3OP4BRT3N6","created_at":"2026-07-05T09:30:24.129787+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUJQZB3O","created_at":"2026-07-05T09:30:24.129787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29537","citing_title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17697","citing_title":"Beyond Syntax: Action Semantics Learning for App Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2508.19679","citing_title":"InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06477","citing_title":"MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10371","citing_title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19396","citing_title":"EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration","ref_index":30,"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":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7","json":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7.json","graph_json":"https://pith.science/api/pith-number/FUJQZB3OP4BRT3N6EWBW47PVH7/graph.json","events_json":"https://pith.science/api/pith-number/FUJQZB3OP4BRT3N6EWBW47PVH7/events.json","paper":"https://pith.science/paper/FUJQZB3O"},"agent_actions":{"view_html":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7","download_json":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7.json","view_paper":"https://pith.science/paper/FUJQZB3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24024&json=true","fetch_graph":"https://pith.science/api/pith-number/FUJQZB3OP4BRT3N6EWBW47PVH7/graph.json","fetch_events":"https://pith.science/api/pith-number/FUJQZB3OP4BRT3N6EWBW47PVH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7/action/storage_attestation","attest_author":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7/action/author_attestation","sign_citation":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7/action/citation_signature","submit_replication":"https://pith.science/pith/FUJQZB3OP4BRT3N6EWBW47PVH7/action/replication_record"}},"created_at":"2026-07-05T09:30:24.129787+00:00","updated_at":"2026-07-05T09:30:24.129787+00:00"}