{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ATEBZBW36U3OEGWELJ34GWWD36","short_pith_number":"pith:ATEBZBW3","schema_version":"1.0","canonical_sha256":"04c81c86dbf536e21ac45a77c35ac3dfbe96968073fe3d759003fc9d685353b8","source":{"kind":"arxiv","id":"2312.03003","version":3},"attestation_state":"computed","paper":{"title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Hojun Choi, Insik Shin, Jungjae Lee, Junyoung Choi, Munim Hasan Wasi, Sangeun Oh, Steven Y. Ko, Sunjae Lee","submitted_at":"2023-12-04T06:13:35Z","abstract_excerpt":"The advent of large language models (LLMs) has opened up new opportunities in the field of mobile task automation. Their superior language understanding and reasoning capabilities allow users to automate complex and repetitive tasks. However, due to the inherent unreliability and high operational cost of LLMs, their practical applicability is quite limited. To address these issues, this paper introduces MobileGPT, an innovative LLM-based mobile task automator equipped with a human-like app memory. MobileGPT emulates the cognitive process of humans interacting with a mobile app -- explore, sele"},"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":"2312.03003","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-12-04T06:13:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d2de1cdc3c107c5f5ad8bf2bcc66fc1172ca84a1a323e4602d538dd7998971bd","abstract_canon_sha256":"93ed09a54229335905b3315db72b646cd0c8d6e155fd11b74bbc2c19fd06a173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:01.791062Z","signature_b64":"23S0R3bFAgT5zoHNvdEqDLHYdNquAOGr85RnLDqjBPu8Us9HXzSCR9UqR2nTTB88+dXU2V5CLhlH/LySaCkFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c81c86dbf536e21ac45a77c35ac3dfbe96968073fe3d759003fc9d685353b8","last_reissued_at":"2026-07-05T09:21:01.790544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:01.790544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Hojun Choi, Insik Shin, Jungjae Lee, Junyoung Choi, Munim Hasan Wasi, Sangeun Oh, Steven Y. Ko, Sunjae Lee","submitted_at":"2023-12-04T06:13:35Z","abstract_excerpt":"The advent of large language models (LLMs) has opened up new opportunities in the field of mobile task automation. Their superior language understanding and reasoning capabilities allow users to automate complex and repetitive tasks. However, due to the inherent unreliability and high operational cost of LLMs, their practical applicability is quite limited. To address these issues, this paper introduces MobileGPT, an innovative LLM-based mobile task automator equipped with a human-like app memory. MobileGPT emulates the cognitive process of humans interacting with a mobile app -- explore, sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03003","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/2312.03003/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":"2312.03003","created_at":"2026-07-05T09:21:01.790610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03003v3","created_at":"2026-07-05T09:21:01.790610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03003","created_at":"2026-07-05T09:21:01.790610+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATEBZBW36U3O","created_at":"2026-07-05T09:21:01.790610+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATEBZBW36U3OEGWE","created_at":"2026-07-05T09:21:01.790610+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATEBZBW3","created_at":"2026-07-05T09:21:01.790610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"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":79,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":281,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03364","citing_title":"DroidRetriever: A Transparent and Steerable Automation System for Collaborative Mobile Information Seeking","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16703","citing_title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06477","citing_title":"MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17817","citing_title":"Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36","json":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36.json","graph_json":"https://pith.science/api/pith-number/ATEBZBW36U3OEGWELJ34GWWD36/graph.json","events_json":"https://pith.science/api/pith-number/ATEBZBW36U3OEGWELJ34GWWD36/events.json","paper":"https://pith.science/paper/ATEBZBW3"},"agent_actions":{"view_html":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36","download_json":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36.json","view_paper":"https://pith.science/paper/ATEBZBW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03003&json=true","fetch_graph":"https://pith.science/api/pith-number/ATEBZBW36U3OEGWELJ34GWWD36/graph.json","fetch_events":"https://pith.science/api/pith-number/ATEBZBW36U3OEGWELJ34GWWD36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36/action/storage_attestation","attest_author":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36/action/author_attestation","sign_citation":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36/action/citation_signature","submit_replication":"https://pith.science/pith/ATEBZBW36U3OEGWELJ34GWWD36/action/replication_record"}},"created_at":"2026-07-05T09:21:01.790610+00:00","updated_at":"2026-07-05T09:21:01.790610+00:00"}