{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C6WXYPBQOXPHIYPRI4UYGD5JE7","short_pith_number":"pith:C6WXYPBQ","schema_version":"1.0","canonical_sha256":"17ad7c3c3075de7461f14729830fa927da5c36dbd4f083955c801b3d1021d9c7","source":{"kind":"arxiv","id":"2504.13805","version":1},"attestation_state":"computed","paper":{"title":"LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Guangyi Liu, Hao Wang, Liang Liu, Pengxiang Zhao, Shibo He, Shuai Ren, Wenchao Meng, Yuxiang Chai, Zhiming Chen","submitted_at":"2025-04-18T17:13:34Z","abstract_excerpt":"Mobile GUI agents show promise in automating tasks but face generalization challenges in diverse real-world scenarios. Traditional approaches using pre-training or fine-tuning with massive datasets struggle with the diversity of mobile applications and user-specific tasks. We propose enhancing mobile GUI agent capabilities through human demonstrations, focusing on improving performance in unseen scenarios rather than pursuing universal generalization through larger datasets. To realize this paradigm, we introduce LearnGUI, the first comprehensive dataset specifically designed for studying demo"},"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":"2504.13805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-18T17:13:34Z","cross_cats_sorted":[],"title_canon_sha256":"f31171b1d3ea6ce903a462c16e82a94282851ea6e9c90c09076ef5150d0a6675","abstract_canon_sha256":"89d7c3cf81831242dc9fde7f422522d993599c933f3a04daee75a0f4c91bbc30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:02.441241Z","signature_b64":"Q5LxJ0joX6/uPYKbliWhIt+ZWAa3aGQQl/mXs5AiUTFw54F5Ua/SotZx6kRkwjAnZMrj3EFNo/UJv4p1951uCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ad7c3c3075de7461f14729830fa927da5c36dbd4f083955c801b3d1021d9c7","last_reissued_at":"2026-07-05T10:51:02.440752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:02.440752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Guangyi Liu, Hao Wang, Liang Liu, Pengxiang Zhao, Shibo He, Shuai Ren, Wenchao Meng, Yuxiang Chai, Zhiming Chen","submitted_at":"2025-04-18T17:13:34Z","abstract_excerpt":"Mobile GUI agents show promise in automating tasks but face generalization challenges in diverse real-world scenarios. Traditional approaches using pre-training or fine-tuning with massive datasets struggle with the diversity of mobile applications and user-specific tasks. We propose enhancing mobile GUI agent capabilities through human demonstrations, focusing on improving performance in unseen scenarios rather than pursuing universal generalization through larger datasets. To realize this paradigm, we introduce LearnGUI, the first comprehensive dataset specifically designed for studying demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13805","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/2504.13805/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":"2504.13805","created_at":"2026-07-05T10:51:02.440810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13805v1","created_at":"2026-07-05T10:51:02.440810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13805","created_at":"2026-07-05T10:51:02.440810+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6WXYPBQOXPH","created_at":"2026-07-05T10:51:02.440810+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6WXYPBQOXPHIYPR","created_at":"2026-07-05T10:51:02.440810+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6WXYPBQ","created_at":"2026-07-05T10:51:02.440810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22385","citing_title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20978","citing_title":"How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20363","citing_title":"Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29445","citing_title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":21,"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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24348","citing_title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10674","citing_title":"Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13531","citing_title":"RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7","json":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7.json","graph_json":"https://pith.science/api/pith-number/C6WXYPBQOXPHIYPRI4UYGD5JE7/graph.json","events_json":"https://pith.science/api/pith-number/C6WXYPBQOXPHIYPRI4UYGD5JE7/events.json","paper":"https://pith.science/paper/C6WXYPBQ"},"agent_actions":{"view_html":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7","download_json":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7.json","view_paper":"https://pith.science/paper/C6WXYPBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13805&json=true","fetch_graph":"https://pith.science/api/pith-number/C6WXYPBQOXPHIYPRI4UYGD5JE7/graph.json","fetch_events":"https://pith.science/api/pith-number/C6WXYPBQOXPHIYPRI4UYGD5JE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7/action/storage_attestation","attest_author":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7/action/author_attestation","sign_citation":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7/action/citation_signature","submit_replication":"https://pith.science/pith/C6WXYPBQOXPHIYPRI4UYGD5JE7/action/replication_record"}},"created_at":"2026-07-05T10:51:02.440810+00:00","updated_at":"2026-07-05T10:51:02.440810+00:00"}