{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2DKEA2IXK7BAF2UGGYZQELUJTY","short_pith_number":"pith:2DKEA2IX","schema_version":"1.0","canonical_sha256":"d0d440691757c202ea863633022e899e0177c44a92e29e319c08378cc589a03c","source":{"kind":"arxiv","id":"2602.06075","version":2},"attestation_state":"computed","paper":{"title":"MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Gao Wu, Guangyi Liu, Han Xiao, Hao Wang, Liang Liu, Pengxiang Zhao, Qinyi Luo, Shunye Tang, Siheng Chen, Weifeng Lin, Wenhao Wang, YaoZhen Liang, Yong Liu, Yuxiang Chai, Zhengxi Lu","submitted_at":"2026-02-03T17:01:59Z","abstract_excerpt":"Reliable mobile GUI agents must retain and reuse information across actions, applications, and repeated interactions. However, current benchmarks systematically underrepresent these memory demands: only 5.2-11.8 percent of their tasks are memory-related, and none evaluates cross-session learning. We introduce MemGUI-Bench, a comprehensive memory-centric benchmark that assesses both short-term information retention and long-term experience accumulation through pass@k protocols and staged LLM-as-judge evaluation. Our contributions include: (1) a systematic taxonomy of short- and long-term memory"},"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":"2602.06075","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-03T17:01:59Z","cross_cats_sorted":[],"title_canon_sha256":"7680889e09bd7b36f783386fe4667da5c32682c4549cbb08bd7dc9239d2b738c","abstract_canon_sha256":"e11f1ea769a146f6daf104a0a68255d765534f42f2f905bba46485f67b4123f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:21:32.476222Z","signature_b64":"yktKNyv6uSYbLaEmIPASZeDgmJ42bsAF6QOwSp27yZmQG9vpZkvQXxjfc8OJHRAALALjrr/A+JaAD/Xy95GiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d440691757c202ea863633022e899e0177c44a92e29e319c08378cc589a03c","last_reissued_at":"2026-08-12T01:21:32.474177Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:21:32.474177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Gao Wu, Guangyi Liu, Han Xiao, Hao Wang, Liang Liu, Pengxiang Zhao, Qinyi Luo, Shunye Tang, Siheng Chen, Weifeng Lin, Wenhao Wang, YaoZhen Liang, Yong Liu, Yuxiang Chai, Zhengxi Lu","submitted_at":"2026-02-03T17:01:59Z","abstract_excerpt":"Reliable mobile GUI agents must retain and reuse information across actions, applications, and repeated interactions. However, current benchmarks systematically underrepresent these memory demands: only 5.2-11.8 percent of their tasks are memory-related, and none evaluates cross-session learning. We introduce MemGUI-Bench, a comprehensive memory-centric benchmark that assesses both short-term information retention and long-term experience accumulation through pass@k protocols and staged LLM-as-judge evaluation. Our contributions include: (1) a systematic taxonomy of short- and long-term memory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06075","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/2602.06075/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":"2602.06075","created_at":"2026-08-12T01:21:32.478124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06075v2","created_at":"2026-08-12T01:21:32.478124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06075","created_at":"2026-08-12T01:21:32.478124+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DKEA2IXK7BA","created_at":"2026-08-12T01:21:32.478124+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DKEA2IXK7BAF2UG","created_at":"2026-08-12T01:21:32.478124+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DKEA2IX","created_at":"2026-08-12T01:21:32.478124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":12,"sample":[{"citing_arxiv_id":"2606.19926","citing_title":"MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31612","citing_title":"What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00502","citing_title":"A Task-State Representation for Long-Horizon Mobile GUI Agents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31612","citing_title":"What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29324","citing_title":"STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14678","citing_title":"$\\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14678","citing_title":"$\\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24348","citing_title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10674","citing_title":"Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":133,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05477","citing_title":"Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13822","citing_title":"UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY","json":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY.json","graph_json":"https://pith.science/api/pith-number/2DKEA2IXK7BAF2UGGYZQELUJTY/graph.json","events_json":"https://pith.science/api/pith-number/2DKEA2IXK7BAF2UGGYZQELUJTY/events.json","paper":"https://pith.science/paper/2DKEA2IX"},"agent_actions":{"view_html":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY","download_json":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY.json","view_paper":"https://pith.science/paper/2DKEA2IX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06075&json=true","fetch_graph":"https://pith.science/api/pith-number/2DKEA2IXK7BAF2UGGYZQELUJTY/graph.json","fetch_events":"https://pith.science/api/pith-number/2DKEA2IXK7BAF2UGGYZQELUJTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY/action/storage_attestation","attest_author":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY/action/author_attestation","sign_citation":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY/action/citation_signature","submit_replication":"https://pith.science/pith/2DKEA2IXK7BAF2UGGYZQELUJTY/action/replication_record"}},"created_at":"2026-08-12T01:21:32.478124+00:00","updated_at":"2026-08-12T01:21:32.478124+00:00"}