{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DJ6M4WHZCRC7EPKB3G4K3RUVVE","short_pith_number":"pith:DJ6M4WHZ","schema_version":"1.0","canonical_sha256":"1a7cce58f91445f23d41d9b8adc695a932d11bd5643dd1fe57ae25d48501acb8","source":{"kind":"arxiv","id":"2407.00993","version":1},"attestation_state":"computed","paper":{"title":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ang Li, Bin Wang, Hongda Sun, Jianfeng Liu, Jian Luan, Rui Yan, Shihan Deng, Shuo Shang, Tao Tan, Weikai Xu, Wei Liu","submitted_at":"2024-07-01T06:10:01Z","abstract_excerpt":"With the remarkable advancements of large language models (LLMs), LLM-based agents have become a research hotspot in human-computer interaction. However, there is a scarcity of benchmarks available for LLM-based mobile agents. Benchmarking these agents generally faces three main challenges: (1) The inefficiency of UI-only operations imposes limitations to task evaluation. (2) Specific instructions within a singular application lack adequacy for assessing the multi-dimensional reasoning and decision-making capacities of LLM mobile agents. (3) Current evaluation metrics are insufficient to accur"},"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":"2407.00993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-01T06:10:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc6354604af2cd1f38112b3fbbc44843866d0acf1319648fa86884622a56946f","abstract_canon_sha256":"85ad21c015bae6dda627551e1a3f2a94753bfad3aa3ff63661486de132e9d0c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:41.201130Z","signature_b64":"iXU5RdoXH7Gfeak/BLLqA6VOHYi6dH07EyBORlm5qWvYrvgLq7TVRRAUuPqH0Kh/q8ekS61WfPtFMChg0h7rBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a7cce58f91445f23d41d9b8adc695a932d11bd5643dd1fe57ae25d48501acb8","last_reissued_at":"2026-07-05T08:38:41.200738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:41.200738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ang Li, Bin Wang, Hongda Sun, Jianfeng Liu, Jian Luan, Rui Yan, Shihan Deng, Shuo Shang, Tao Tan, Weikai Xu, Wei Liu","submitted_at":"2024-07-01T06:10:01Z","abstract_excerpt":"With the remarkable advancements of large language models (LLMs), LLM-based agents have become a research hotspot in human-computer interaction. However, there is a scarcity of benchmarks available for LLM-based mobile agents. Benchmarking these agents generally faces three main challenges: (1) The inefficiency of UI-only operations imposes limitations to task evaluation. (2) Specific instructions within a singular application lack adequacy for assessing the multi-dimensional reasoning and decision-making capacities of LLM mobile agents. (3) Current evaluation metrics are insufficient to accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00993","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/2407.00993/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":"2407.00993","created_at":"2026-07-05T08:38:41.200793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00993v1","created_at":"2026-07-05T08:38:41.200793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00993","created_at":"2026-07-05T08:38:41.200793+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJ6M4WHZCRC7","created_at":"2026-07-05T08:38:41.200793+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJ6M4WHZCRC7EPKB","created_at":"2026-07-05T08:38:41.200793+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJ6M4WHZ","created_at":"2026-07-05T08:38:41.200793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29537","citing_title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11763","citing_title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10866","citing_title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE","json":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE.json","graph_json":"https://pith.science/api/pith-number/DJ6M4WHZCRC7EPKB3G4K3RUVVE/graph.json","events_json":"https://pith.science/api/pith-number/DJ6M4WHZCRC7EPKB3G4K3RUVVE/events.json","paper":"https://pith.science/paper/DJ6M4WHZ"},"agent_actions":{"view_html":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE","download_json":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE.json","view_paper":"https://pith.science/paper/DJ6M4WHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00993&json=true","fetch_graph":"https://pith.science/api/pith-number/DJ6M4WHZCRC7EPKB3G4K3RUVVE/graph.json","fetch_events":"https://pith.science/api/pith-number/DJ6M4WHZCRC7EPKB3G4K3RUVVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE/action/storage_attestation","attest_author":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE/action/author_attestation","sign_citation":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE/action/citation_signature","submit_replication":"https://pith.science/pith/DJ6M4WHZCRC7EPKB3G4K3RUVVE/action/replication_record"}},"created_at":"2026-07-05T08:38:41.200793+00:00","updated_at":"2026-07-05T08:38:41.200793+00:00"}