{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P67FOEU5TMCNLCBNUPUKBAKFZ3","short_pith_number":"pith:P67FOEU5","schema_version":"1.0","canonical_sha256":"7fbe57129d9b04d5882da3e8a08145ceeb525fabb59c01f640f1fe6b29936ef7","source":{"kind":"arxiv","id":"2412.18116","version":3},"attestation_state":"computed","paper":{"title":"AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Borislav Pavlov, Ge Chang, Hao Wen, Jiacheng Liu, Shanhui Zhao, Shizuo Tian, Wenjie Du, Ya-Qin Zhang, Yixuan Li, Yuanchun Li, Yunxin Liu","submitted_at":"2024-12-24T02:54:56Z","abstract_excerpt":"Large language models (LLMs) have brought exciting new advances to mobile UI agents, a long-standing research field that aims to complete arbitrary natural language tasks through mobile UI interactions. However, existing UI agents usually demand powerful large language models that are difficult to be deployed locally on end-users' devices, raising huge concerns about user privacy and centralized serving cost. Inspired by the remarkable coding abilities of recent small language models (SLMs), we propose to convert the UI task automation problem to a code generation problem, which can be effecti"},"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":"2412.18116","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T02:54:56Z","cross_cats_sorted":[],"title_canon_sha256":"dd23542d60f9347770be45a6ab46ffc90d03843d7753033f1bb47803141d31bb","abstract_canon_sha256":"6c89a51cf57990ce4d1bbd2e1a90402978193cd3d493295c8355d3de5012d989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:04.622796Z","signature_b64":"9etOqvRt9kY1zIDWbChSNXB3kNpZtm54gkJaahwE/NagIvkknWIiHC/kmQUxG3sWS09L+PeAHpU8/cLAdgL8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fbe57129d9b04d5882da3e8a08145ceeb525fabb59c01f640f1fe6b29936ef7","last_reissued_at":"2026-07-05T10:59:04.622261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:04.622261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Borislav Pavlov, Ge Chang, Hao Wen, Jiacheng Liu, Shanhui Zhao, Shizuo Tian, Wenjie Du, Ya-Qin Zhang, Yixuan Li, Yuanchun Li, Yunxin Liu","submitted_at":"2024-12-24T02:54:56Z","abstract_excerpt":"Large language models (LLMs) have brought exciting new advances to mobile UI agents, a long-standing research field that aims to complete arbitrary natural language tasks through mobile UI interactions. However, existing UI agents usually demand powerful large language models that are difficult to be deployed locally on end-users' devices, raising huge concerns about user privacy and centralized serving cost. Inspired by the remarkable coding abilities of recent small language models (SLMs), we propose to convert the UI task automation problem to a code generation problem, which can be effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18116","kind":"arxiv","version":3},"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/2412.18116/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":"2412.18116","created_at":"2026-07-05T10:59:04.622324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18116v3","created_at":"2026-07-05T10:59:04.622324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18116","created_at":"2026-07-05T10:59:04.622324+00:00"},{"alias_kind":"pith_short_12","alias_value":"P67FOEU5TMCN","created_at":"2026-07-05T10:59:04.622324+00:00"},{"alias_kind":"pith_short_16","alias_value":"P67FOEU5TMCNLCBN","created_at":"2026-07-05T10:59:04.622324+00:00"},{"alias_kind":"pith_short_8","alias_value":"P67FOEU5","created_at":"2026-07-05T10:59:04.622324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":27,"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":35,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":38,"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":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3","json":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3.json","graph_json":"https://pith.science/api/pith-number/P67FOEU5TMCNLCBNUPUKBAKFZ3/graph.json","events_json":"https://pith.science/api/pith-number/P67FOEU5TMCNLCBNUPUKBAKFZ3/events.json","paper":"https://pith.science/paper/P67FOEU5"},"agent_actions":{"view_html":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3","download_json":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3.json","view_paper":"https://pith.science/paper/P67FOEU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18116&json=true","fetch_graph":"https://pith.science/api/pith-number/P67FOEU5TMCNLCBNUPUKBAKFZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/P67FOEU5TMCNLCBNUPUKBAKFZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3/action/storage_attestation","attest_author":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3/action/author_attestation","sign_citation":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3/action/citation_signature","submit_replication":"https://pith.science/pith/P67FOEU5TMCNLCBNUPUKBAKFZ3/action/replication_record"}},"created_at":"2026-07-05T10:59:04.622324+00:00","updated_at":"2026-07-05T10:59:04.622324+00:00"}