{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OZHBDST6XNT6BQAD5CI7F6YYAU","short_pith_number":"pith:OZHBDST6","schema_version":"1.0","canonical_sha256":"764e11ca7ebb67e0c003e891f2fb18050299da0025d736a89b35b8ef7d8e2670","source":{"kind":"arxiv","id":"2407.04346","version":3},"attestation_state":"computed","paper":{"title":"MobileFlow: A Multimodal LLM For Mobile GUI Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiali Zhu, Jiongchao Jin, Rui Wu, Shuo Shan, Songqin Nong, Wenhao Xu, Xiutian Huang","submitted_at":"2024-07-05T08:37:10Z","abstract_excerpt":"Currently, the integration of mobile Graphical User Interfaces (GUIs) is ubiquitous in most people's daily lives. And the ongoing evolution of multimodal large-scale models, such as GPT-4v, Qwen-VL-Max, has significantly bolstered the capabilities of GUI comprehension and user action analysis, showcasing the potentiality of intelligent GUI assistants. However, current GUI Agents often need to access page layout information through calling system APIs, which may pose privacy risks. Fixing GUI (such as mobile interfaces) to a certain low resolution might result in the loss of fine-grained image "},"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":"2407.04346","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T08:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"549a9ffb0ee5f848b493cd39140508a16364e847f1af900f21569e0c7212083a","abstract_canon_sha256":"a81dd21f9e85f29ad7a677c9309be2844a47cc104eb823be796f1544dcb83e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:11.623966Z","signature_b64":"nsk1iZEuUX/j2su8gab5fjLyVhcKoeSViGoJiXyli8SLlngNzALKTs/O4dpf7g+pwJ95kg3PRkBMqSSrwkrKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"764e11ca7ebb67e0c003e891f2fb18050299da0025d736a89b35b8ef7d8e2670","last_reissued_at":"2026-07-05T09:45:11.623475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:11.623475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileFlow: A Multimodal LLM For Mobile GUI Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiali Zhu, Jiongchao Jin, Rui Wu, Shuo Shan, Songqin Nong, Wenhao Xu, Xiutian Huang","submitted_at":"2024-07-05T08:37:10Z","abstract_excerpt":"Currently, the integration of mobile Graphical User Interfaces (GUIs) is ubiquitous in most people's daily lives. And the ongoing evolution of multimodal large-scale models, such as GPT-4v, Qwen-VL-Max, has significantly bolstered the capabilities of GUI comprehension and user action analysis, showcasing the potentiality of intelligent GUI assistants. However, current GUI Agents often need to access page layout information through calling system APIs, which may pose privacy risks. Fixing GUI (such as mobile interfaces) to a certain low resolution might result in the loss of fine-grained image "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04346","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/2407.04346/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":"2407.04346","created_at":"2026-07-05T09:45:11.623530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04346v3","created_at":"2026-07-05T09:45:11.623530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04346","created_at":"2026-07-05T09:45:11.623530+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZHBDST6XNT6","created_at":"2026-07-05T09:45:11.623530+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZHBDST6XNT6BQAD","created_at":"2026-07-05T09:45:11.623530+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZHBDST6","created_at":"2026-07-05T09:45:11.623530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03976","citing_title":"Quantifying Trust: Financial Risk Management for Trustworthy AI Agents","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17284","citing_title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU","json":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU.json","graph_json":"https://pith.science/api/pith-number/OZHBDST6XNT6BQAD5CI7F6YYAU/graph.json","events_json":"https://pith.science/api/pith-number/OZHBDST6XNT6BQAD5CI7F6YYAU/events.json","paper":"https://pith.science/paper/OZHBDST6"},"agent_actions":{"view_html":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU","download_json":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU.json","view_paper":"https://pith.science/paper/OZHBDST6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04346&json=true","fetch_graph":"https://pith.science/api/pith-number/OZHBDST6XNT6BQAD5CI7F6YYAU/graph.json","fetch_events":"https://pith.science/api/pith-number/OZHBDST6XNT6BQAD5CI7F6YYAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU/action/storage_attestation","attest_author":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU/action/author_attestation","sign_citation":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU/action/citation_signature","submit_replication":"https://pith.science/pith/OZHBDST6XNT6BQAD5CI7F6YYAU/action/replication_record"}},"created_at":"2026-07-05T09:45:11.623530+00:00","updated_at":"2026-07-05T09:45:11.623530+00:00"}