{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PGXY4FAEWVBNKKEEYYZODZZFKF","short_pith_number":"pith:PGXY4FAE","schema_version":"1.0","canonical_sha256":"79af8e1404b542d52884c632e1e7255142e682fb5577f60fdf257ee33cb7e0b1","source":{"kind":"arxiv","id":"2209.08655","version":2},"attestation_state":"computed","paper":{"title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Bryan Wang, Gang Li, Yang Li","submitted_at":"2022-09-18T20:58:39Z","abstract_excerpt":"Conversational agents show the promise to allow users to interact with mobile devices using language. However, to perform diverse UI tasks with natural language, developers typically need to create separate datasets and models for each specific task, which is expensive and effort-consuming. Recently, pre-trained large language models (LLMs) have been shown capable of generalizing to various downstream tasks when prompted with a handful of examples from the target task. This paper investigates the feasibility of enabling versatile conversational interactions with mobile UIs using a single LLM. "},"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":"2209.08655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2022-09-18T20:58:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b21e25a98705a9a69732e078aa2bec102f0c4b1a0726df0d4a1e63ecc74f572","abstract_canon_sha256":"1248b32787319a57e256e17d42ea4b5dde28f4e7d43663f7e3ca581ba04408d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:15.244559Z","signature_b64":"pfw7JUNNMDTyxK90wu8uTlLxiA9dcJ2F28cHo77ZgPfly4aAb6RYTy92oXOg4E+uJDOx4ZrUB61EfZBeL3VZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79af8e1404b542d52884c632e1e7255142e682fb5577f60fdf257ee33cb7e0b1","last_reissued_at":"2026-07-05T05:43:15.244101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:15.244101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Bryan Wang, Gang Li, Yang Li","submitted_at":"2022-09-18T20:58:39Z","abstract_excerpt":"Conversational agents show the promise to allow users to interact with mobile devices using language. However, to perform diverse UI tasks with natural language, developers typically need to create separate datasets and models for each specific task, which is expensive and effort-consuming. Recently, pre-trained large language models (LLMs) have been shown capable of generalizing to various downstream tasks when prompted with a handful of examples from the target task. This paper investigates the feasibility of enabling versatile conversational interactions with mobile UIs using a single LLM. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08655","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/2209.08655/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":"2209.08655","created_at":"2026-07-05T05:43:15.244150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08655v2","created_at":"2026-07-05T05:43:15.244150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08655","created_at":"2026-07-05T05:43:15.244150+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGXY4FAEWVBN","created_at":"2026-07-05T05:43:15.244150+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGXY4FAEWVBNKKEE","created_at":"2026-07-05T05:43:15.244150+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGXY4FAE","created_at":"2026-07-05T05:43:15.244150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17656","citing_title":"MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF","json":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF.json","graph_json":"https://pith.science/api/pith-number/PGXY4FAEWVBNKKEEYYZODZZFKF/graph.json","events_json":"https://pith.science/api/pith-number/PGXY4FAEWVBNKKEEYYZODZZFKF/events.json","paper":"https://pith.science/paper/PGXY4FAE"},"agent_actions":{"view_html":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF","download_json":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF.json","view_paper":"https://pith.science/paper/PGXY4FAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08655&json=true","fetch_graph":"https://pith.science/api/pith-number/PGXY4FAEWVBNKKEEYYZODZZFKF/graph.json","fetch_events":"https://pith.science/api/pith-number/PGXY4FAEWVBNKKEEYYZODZZFKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF/action/storage_attestation","attest_author":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF/action/author_attestation","sign_citation":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF/action/citation_signature","submit_replication":"https://pith.science/pith/PGXY4FAEWVBNKKEEYYZODZZFKF/action/replication_record"}},"created_at":"2026-07-05T05:43:15.244150+00:00","updated_at":"2026-07-05T05:43:15.244150+00:00"}