{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BFLCI6OMJELPSUP3BKJ6CGXE72","short_pith_number":"pith:BFLCI6OM","schema_version":"1.0","canonical_sha256":"09562479cc4916f951fb0a93e11ae4fe928c989c7c04261b197dfc8cec1167c0","source":{"kind":"arxiv","id":"2205.11029","version":2},"attestation_state":"computed","paper":{"title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai Yu, Liangtai Sun, Lu Chen, Tianle Dai, Xingyu Chen, Zichen Zhu","submitted_at":"2022-05-23T04:05:37Z","abstract_excerpt":"Task-oriented dialogue (TOD) systems have been widely used by mobile phone intelligent assistants to accomplish tasks such as calendar scheduling or hotel reservation. Current TOD systems usually focus on multi-turn text/speech interaction, then they would call back-end APIs designed for TODs to perform the task. However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs. In this paper, we propose a n"},"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":"2205.11029","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T04:05:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"66737f554c1d4e2af9da651bec2b66417e2e8fc361e4c0301cbdad778ba92681","abstract_canon_sha256":"c2df3c410a948103de63c0f50d2de0d1f3b2102947dae899f100f5af7bbf75da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:47.515346Z","signature_b64":"q+6C547RGlQpsfRRq7ewQoTo2XoNj7Cz/zu4724XbPlRzjdQVj64MH2UW8gIvb2zGPeodSR+qfjxJ8wpltJkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09562479cc4916f951fb0a93e11ae4fe928c989c7c04261b197dfc8cec1167c0","last_reissued_at":"2026-07-05T07:50:47.514834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:47.514834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai Yu, Liangtai Sun, Lu Chen, Tianle Dai, Xingyu Chen, Zichen Zhu","submitted_at":"2022-05-23T04:05:37Z","abstract_excerpt":"Task-oriented dialogue (TOD) systems have been widely used by mobile phone intelligent assistants to accomplish tasks such as calendar scheduling or hotel reservation. Current TOD systems usually focus on multi-turn text/speech interaction, then they would call back-end APIs designed for TODs to perform the task. However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs. In this paper, we propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11029","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/2205.11029/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":"2205.11029","created_at":"2026-07-05T07:50:47.514892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11029v2","created_at":"2026-07-05T07:50:47.514892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11029","created_at":"2026-07-05T07:50:47.514892+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFLCI6OMJELP","created_at":"2026-07-05T07:50:47.514892+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFLCI6OMJELPSUP3","created_at":"2026-07-05T07:50:47.514892+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFLCI6OM","created_at":"2026-07-05T07:50:47.514892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"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":54,"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":99,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10371","citing_title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":29,"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":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06134","citing_title":"MAESTRO: Adapting GUIs and Guiding Navigation with User Preferences in Conversational Agents with GUIs","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72","json":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72.json","graph_json":"https://pith.science/api/pith-number/BFLCI6OMJELPSUP3BKJ6CGXE72/graph.json","events_json":"https://pith.science/api/pith-number/BFLCI6OMJELPSUP3BKJ6CGXE72/events.json","paper":"https://pith.science/paper/BFLCI6OM"},"agent_actions":{"view_html":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72","download_json":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72.json","view_paper":"https://pith.science/paper/BFLCI6OM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11029&json=true","fetch_graph":"https://pith.science/api/pith-number/BFLCI6OMJELPSUP3BKJ6CGXE72/graph.json","fetch_events":"https://pith.science/api/pith-number/BFLCI6OMJELPSUP3BKJ6CGXE72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72/action/storage_attestation","attest_author":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72/action/author_attestation","sign_citation":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72/action/citation_signature","submit_replication":"https://pith.science/pith/BFLCI6OMJELPSUP3BKJ6CGXE72/action/replication_record"}},"created_at":"2026-07-05T07:50:47.514892+00:00","updated_at":"2026-07-05T07:50:47.514892+00:00"}