{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JCMQVKHDSE7YFLASMUPQ3BJ46S","short_pith_number":"pith:JCMQVKHD","schema_version":"1.0","canonical_sha256":"48990aa8e3913f82ac12651f0d853cf4823824ad1c9b6454e17c6602e8e9ab49","source":{"kind":"arxiv","id":"2307.10088","version":2},"attestation_state":"computed","paper":{"title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.LG","authors_text":"Alice Li, Christopher Rawles, Daniel Rodriguez, Oriana Riva, Timothy Lillicrap","submitted_at":"2023-07-19T15:57:24Z","abstract_excerpt":"There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling its user interface. We present a dataset for device-control research, Android in the Wild (AITW), which is orders of magnitude larger than current datasets. The dataset contains human demonstrations of device interactions, including the screens and actions, and corresponding natural language instructions. It consists of 715k episodes spanning 30k unique instructions, four versions of Android (v10-13),and eight device types (Pi"},"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":"2307.10088","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-19T15:57:24Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"0c1869087ca67a34e498d3537214a64fa19c6ee8da54ceb9db7962bee1fcd481","abstract_canon_sha256":"78ac6ea376cbc32a3e166a8ed4ba5645b08cdc31ea1de33b3611e7769c68c4dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:46.269886Z","signature_b64":"AoOzTzk2bIMlIowNR9q711WHVhXB7pcRTDrhS/l227Ln/lXfy9IFd1WUXTrND53DgdhC92h9+l3bkYvPkd/kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48990aa8e3913f82ac12651f0d853cf4823824ad1c9b6454e17c6602e8e9ab49","last_reissued_at":"2026-07-05T07:05:46.269393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:46.269393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.LG","authors_text":"Alice Li, Christopher Rawles, Daniel Rodriguez, Oriana Riva, Timothy Lillicrap","submitted_at":"2023-07-19T15:57:24Z","abstract_excerpt":"There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling its user interface. We present a dataset for device-control research, Android in the Wild (AITW), which is orders of magnitude larger than current datasets. The dataset contains human demonstrations of device interactions, including the screens and actions, and corresponding natural language instructions. It consists of 715k episodes spanning 30k unique instructions, four versions of Android (v10-13),and eight device types (Pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10088","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/2307.10088/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":"2307.10088","created_at":"2026-07-05T07:05:46.269450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10088v2","created_at":"2026-07-05T07:05:46.269450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10088","created_at":"2026-07-05T07:05:46.269450+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCMQVKHDSE7Y","created_at":"2026-07-05T07:05:46.269450+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCMQVKHDSE7YFLAS","created_at":"2026-07-05T07:05:46.269450+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCMQVKHD","created_at":"2026-07-05T07:05:46.269450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23049","citing_title":"PhoneBuddy: Training Open Models for Agentic Phone Use","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03854","citing_title":"CLI-Anything: Towards Agent-Native Computer Use","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":49,"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":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26546","citing_title":"MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":58,"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":130,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05765","citing_title":"X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":22,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08526","citing_title":"Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26148","citing_title":"Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05765","citing_title":"X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction","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":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S","json":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S.json","graph_json":"https://pith.science/api/pith-number/JCMQVKHDSE7YFLASMUPQ3BJ46S/graph.json","events_json":"https://pith.science/api/pith-number/JCMQVKHDSE7YFLASMUPQ3BJ46S/events.json","paper":"https://pith.science/paper/JCMQVKHD"},"agent_actions":{"view_html":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S","download_json":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S.json","view_paper":"https://pith.science/paper/JCMQVKHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10088&json=true","fetch_graph":"https://pith.science/api/pith-number/JCMQVKHDSE7YFLASMUPQ3BJ46S/graph.json","fetch_events":"https://pith.science/api/pith-number/JCMQVKHDSE7YFLASMUPQ3BJ46S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S/action/storage_attestation","attest_author":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S/action/author_attestation","sign_citation":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S/action/citation_signature","submit_replication":"https://pith.science/pith/JCMQVKHDSE7YFLASMUPQ3BJ46S/action/replication_record"}},"created_at":"2026-07-05T07:05:46.269450+00:00","updated_at":"2026-07-05T07:05:46.269450+00:00"}