{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G2GLUTL57KSJ5BKE6VMULZYNZE","short_pith_number":"pith:G2GLUTL5","schema_version":"1.0","canonical_sha256":"368cba4d7dfaa49e8544f55945e70dc93f96581269e0090d2a8f00442233fb9b","source":{"kind":"arxiv","id":"2504.15917","version":2},"attestation_state":"computed","paper":{"title":"Towards Test Generation from Task Description for Mobile Testing with Multi-modal Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hai Phung, Hao Pham, Hieu Huynh, Tien N. Nguyen, Vu Nguyen","submitted_at":"2025-04-22T14:02:57Z","abstract_excerpt":"In Android GUI testing, generating an action sequence for a task that can be replayed as a test script is common. Generating sequences of actions and respective test scripts from task goals described in natural language can eliminate the need for manually writing test scripts. However, existing approaches based on large language models (LLM) often struggle with identifying the final action, and either end prematurely or continue past the final screen. In this paper, we introduce VisiDroid, a multi-modal, LLM-based, multi-agent framework that iteratively determines the next action and leverages"},"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":"2504.15917","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-22T14:02:57Z","cross_cats_sorted":[],"title_canon_sha256":"b71a0275eb7588ae1193069f8217a3021548a4183bbfb187d888d1492db48731","abstract_canon_sha256":"85652bcf74ec51976ececf6a3fa34e23ab749fc2119da4ab306fd34b2d28e778"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:16.742187Z","signature_b64":"909Loi1xfSHRyXA4Nk/mdLrMoAkI6LeL87DUpRqoi6qhEqeNTm8s0kd97+HOvwsi2clNBLPAmqZ81hvvDbbVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"368cba4d7dfaa49e8544f55945e70dc93f96581269e0090d2a8f00442233fb9b","last_reissued_at":"2026-07-05T12:09:16.741560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:16.741560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Test Generation from Task Description for Mobile Testing with Multi-modal Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hai Phung, Hao Pham, Hieu Huynh, Tien N. Nguyen, Vu Nguyen","submitted_at":"2025-04-22T14:02:57Z","abstract_excerpt":"In Android GUI testing, generating an action sequence for a task that can be replayed as a test script is common. Generating sequences of actions and respective test scripts from task goals described in natural language can eliminate the need for manually writing test scripts. However, existing approaches based on large language models (LLM) often struggle with identifying the final action, and either end prematurely or continue past the final screen. In this paper, we introduce VisiDroid, a multi-modal, LLM-based, multi-agent framework that iteratively determines the next action and leverages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15917","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/2504.15917/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":"2504.15917","created_at":"2026-07-05T12:09:16.741637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15917v2","created_at":"2026-07-05T12:09:16.741637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15917","created_at":"2026-07-05T12:09:16.741637+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2GLUTL57KSJ","created_at":"2026-07-05T12:09:16.741637+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2GLUTL57KSJ5BKE","created_at":"2026-07-05T12:09:16.741637+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2GLUTL5","created_at":"2026-07-05T12:09:16.741637+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":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE","json":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE.json","graph_json":"https://pith.science/api/pith-number/G2GLUTL57KSJ5BKE6VMULZYNZE/graph.json","events_json":"https://pith.science/api/pith-number/G2GLUTL57KSJ5BKE6VMULZYNZE/events.json","paper":"https://pith.science/paper/G2GLUTL5"},"agent_actions":{"view_html":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE","download_json":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE.json","view_paper":"https://pith.science/paper/G2GLUTL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15917&json=true","fetch_graph":"https://pith.science/api/pith-number/G2GLUTL57KSJ5BKE6VMULZYNZE/graph.json","fetch_events":"https://pith.science/api/pith-number/G2GLUTL57KSJ5BKE6VMULZYNZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE/action/storage_attestation","attest_author":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE/action/author_attestation","sign_citation":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE/action/citation_signature","submit_replication":"https://pith.science/pith/G2GLUTL57KSJ5BKE6VMULZYNZE/action/replication_record"}},"created_at":"2026-07-05T12:09:16.741637+00:00","updated_at":"2026-07-05T12:09:16.741637+00:00"}