{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ILDDWXMXFUGPI4ZIEWN4RGOHDJ","short_pith_number":"pith:ILDDWXMX","schema_version":"1.0","canonical_sha256":"42c63b5d972d0cf47328259bc899c71a6e307fcee7570b9e1e8975b175b2e08d","source":{"kind":"arxiv","id":"2509.00366","version":1},"attestation_state":"computed","paper":{"title":"KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.MA","authors_text":"Donglai Xu, Graziano Chesi, Jason Chun Lok Li, Jinpeng Chen, Mengyang Wu, Ngai Wong, Pengfei Xian, Pingping Zhang, Shengchao Qin, Thanh-Toan Nguyen, Wenao Ma, Yuzhi Zhao, Zhijian Hou, Ziyi Guan","submitted_at":"2025-08-30T05:32:32Z","abstract_excerpt":"Despite recent progress, Graphic User Interface (GUI) agents powered by Large Language Models (LLMs) struggle with complex mobile tasks due to limited app-specific knowledge. While UI Transition Graphs (UTGs) offer structured navigation representations, they are underutilized due to poor extraction and inefficient integration. We introduce KG-RAG, a Knowledge Graph-driven Retrieval-Augmented Generation framework that transforms fragmented UTGs into structured vector databases for efficient real-time retrieval. By leveraging an intent-guided LLM search method, KG-RAG generates actionable naviga"},"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":"2509.00366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-08-30T05:32:32Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"9f967314fb565ac5b7418b2ad6d1be3e1baa9c646804f0801c5a39ed940521ef","abstract_canon_sha256":"52dc2acbaf9c0367aa801d7fab47018f4f7a7a3aa10e922cc7210ee30bf7d61b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:14.783402Z","signature_b64":"BduC5B/+mgIqXIKX2VO/x7b0kpTL1aokyWrtAFwKcc52pcK7Y2QMvsdiRvhIlz+ONKm7kz+efVRciRXs7B2mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42c63b5d972d0cf47328259bc899c71a6e307fcee7570b9e1e8975b175b2e08d","last_reissued_at":"2026-07-05T12:02:14.782886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:14.782886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.MA","authors_text":"Donglai Xu, Graziano Chesi, Jason Chun Lok Li, Jinpeng Chen, Mengyang Wu, Ngai Wong, Pengfei Xian, Pingping Zhang, Shengchao Qin, Thanh-Toan Nguyen, Wenao Ma, Yuzhi Zhao, Zhijian Hou, Ziyi Guan","submitted_at":"2025-08-30T05:32:32Z","abstract_excerpt":"Despite recent progress, Graphic User Interface (GUI) agents powered by Large Language Models (LLMs) struggle with complex mobile tasks due to limited app-specific knowledge. While UI Transition Graphs (UTGs) offer structured navigation representations, they are underutilized due to poor extraction and inefficient integration. We introduce KG-RAG, a Knowledge Graph-driven Retrieval-Augmented Generation framework that transforms fragmented UTGs into structured vector databases for efficient real-time retrieval. By leveraging an intent-guided LLM search method, KG-RAG generates actionable naviga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00366","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/2509.00366/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":"2509.00366","created_at":"2026-07-05T12:02:14.782950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00366v1","created_at":"2026-07-05T12:02:14.782950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00366","created_at":"2026-07-05T12:02:14.782950+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILDDWXMXFUGP","created_at":"2026-07-05T12:02:14.782950+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILDDWXMXFUGPI4ZI","created_at":"2026-07-05T12:02:14.782950+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILDDWXMX","created_at":"2026-07-05T12:02:14.782950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ","json":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ.json","graph_json":"https://pith.science/api/pith-number/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/graph.json","events_json":"https://pith.science/api/pith-number/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/events.json","paper":"https://pith.science/paper/ILDDWXMX"},"agent_actions":{"view_html":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ","download_json":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ.json","view_paper":"https://pith.science/paper/ILDDWXMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00366&json=true","fetch_graph":"https://pith.science/api/pith-number/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/action/storage_attestation","attest_author":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/action/author_attestation","sign_citation":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/action/citation_signature","submit_replication":"https://pith.science/pith/ILDDWXMXFUGPI4ZIEWN4RGOHDJ/action/replication_record"}},"created_at":"2026-07-05T12:02:14.782950+00:00","updated_at":"2026-07-05T12:02:14.782950+00:00"}