{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CXA5ZPSD3ZNG23LQBEV7VEBRYW","short_pith_number":"pith:CXA5ZPSD","schema_version":"1.0","canonical_sha256":"15c1dcbe43de5a6d6d70092bfa9031c5bae9485e033da27d71f79a16614c036d","source":{"kind":"arxiv","id":"2311.08649","version":1},"attestation_state":"computed","paper":{"title":"Autonomous Large Language Model Agents Enabling Intent-Driven Mobile GUI Testing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Juyeon Yoon, Robert Feldt, Shin Yoo","submitted_at":"2023-11-15T01:59:40Z","abstract_excerpt":"GUI testing checks if a software system behaves as expected when users interact with its graphical interface, e.g., testing specific functionality or validating relevant use case scenarios. Currently, deciding what to test at this high level is a manual task since automated GUI testing tools target lower level adequacy metrics such as structural code coverage or activity coverage. We propose DroidAgent, an autonomous GUI testing agent for Android, for semantic, intent-driven automation of GUI testing. It is based on Large Language Models and support mechanisms such as long- and short-term memo"},"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":"2311.08649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2023-11-15T01:59:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87b48387c271e63418366af6446520eb34cbdb10f24f671e877795e9f3683949","abstract_canon_sha256":"3a4fe3fcee03b05d7ee97add79eb6f56f6c36ebe0ad4ae84a364ef0d437e323d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:00.926748Z","signature_b64":"qUAqg4NbFUWkgC63rCpK1vVOMsjtxJTOqW4K5KYiFiL615P7bNyo+7qB/tbwJCEpbGH8RYitl6MlUBMn5ziGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c1dcbe43de5a6d6d70092bfa9031c5bae9485e033da27d71f79a16614c036d","last_reissued_at":"2026-07-05T07:13:00.926322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:00.926322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autonomous Large Language Model Agents Enabling Intent-Driven Mobile GUI Testing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Juyeon Yoon, Robert Feldt, Shin Yoo","submitted_at":"2023-11-15T01:59:40Z","abstract_excerpt":"GUI testing checks if a software system behaves as expected when users interact with its graphical interface, e.g., testing specific functionality or validating relevant use case scenarios. Currently, deciding what to test at this high level is a manual task since automated GUI testing tools target lower level adequacy metrics such as structural code coverage or activity coverage. We propose DroidAgent, an autonomous GUI testing agent for Android, for semantic, intent-driven automation of GUI testing. It is based on Large Language Models and support mechanisms such as long- and short-term memo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08649","kind":"arxiv","version":1},"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/2311.08649/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":"2311.08649","created_at":"2026-07-05T07:13:00.926383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08649v1","created_at":"2026-07-05T07:13:00.926383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08649","created_at":"2026-07-05T07:13:00.926383+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXA5ZPSD3ZNG","created_at":"2026-07-05T07:13:00.926383+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXA5ZPSD3ZNG23LQ","created_at":"2026-07-05T07:13:00.926383+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXA5ZPSD","created_at":"2026-07-05T07:13:00.926383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28750","citing_title":"DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW","json":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW.json","graph_json":"https://pith.science/api/pith-number/CXA5ZPSD3ZNG23LQBEV7VEBRYW/graph.json","events_json":"https://pith.science/api/pith-number/CXA5ZPSD3ZNG23LQBEV7VEBRYW/events.json","paper":"https://pith.science/paper/CXA5ZPSD"},"agent_actions":{"view_html":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW","download_json":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW.json","view_paper":"https://pith.science/paper/CXA5ZPSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08649&json=true","fetch_graph":"https://pith.science/api/pith-number/CXA5ZPSD3ZNG23LQBEV7VEBRYW/graph.json","fetch_events":"https://pith.science/api/pith-number/CXA5ZPSD3ZNG23LQBEV7VEBRYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW/action/storage_attestation","attest_author":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW/action/author_attestation","sign_citation":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW/action/citation_signature","submit_replication":"https://pith.science/pith/CXA5ZPSD3ZNG23LQBEV7VEBRYW/action/replication_record"}},"created_at":"2026-07-05T07:13:00.926383+00:00","updated_at":"2026-07-05T07:13:00.926383+00:00"}