{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y5HWUN2I7KEJ6YNNDRINE4Z6SQ","short_pith_number":"pith:Y5HWUN2I","schema_version":"1.0","canonical_sha256":"c74f6a3748fa889f61ad1c50d2733e943a84ea2e7dba3c9b8cb9ca8c90023066","source":{"kind":"arxiv","id":"2404.05719","version":1},"attestation_state":"computed","paper":{"title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Amanda Swearngin, Eldon Schoop, Floris Weers, Haotian Zhang, Jeffrey Nichols, Keen You, Yinfei Yang, Zhe Gan","submitted_at":"2024-04-08T17:55:44Z","abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have been noteworthy, yet, these general-domain MLLMs often fall short in their ability to comprehend and interact effectively with user interface (UI) screens. In this paper, we present Ferret-UI, a new MLLM tailored for enhanced understanding of mobile UI screens, equipped with referring, grounding, and reasoning capabilities. Given that UI screens typically exhibit a more elongated aspect ratio and contain smaller objects of interest (e.g., icons, texts) than natural images, we incorporate \"any resolution\" on top of Ferret to m"},"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":"2404.05719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:55:44Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"2374986aa2698a29fda01b13824b885d548344e8c8257dc9e18387fe41c27024","abstract_canon_sha256":"5a1e7b8d28abd3158e074f6fbed62b6dadf76b52f1517afabf601c81498c2639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:44.613704Z","signature_b64":"IuFqw940QMifbDhXtBySa6fOQtZfjindUjx5AcDxHUzgCxDF7OOtAsTra9pX34uvstbvVqyQ6GRqmlXecTUWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c74f6a3748fa889f61ad1c50d2733e943a84ea2e7dba3c9b8cb9ca8c90023066","last_reissued_at":"2026-07-05T08:05:44.613267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:44.613267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Amanda Swearngin, Eldon Schoop, Floris Weers, Haotian Zhang, Jeffrey Nichols, Keen You, Yinfei Yang, Zhe Gan","submitted_at":"2024-04-08T17:55:44Z","abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have been noteworthy, yet, these general-domain MLLMs often fall short in their ability to comprehend and interact effectively with user interface (UI) screens. In this paper, we present Ferret-UI, a new MLLM tailored for enhanced understanding of mobile UI screens, equipped with referring, grounding, and reasoning capabilities. Given that UI screens typically exhibit a more elongated aspect ratio and contain smaller objects of interest (e.g., icons, texts) than natural images, we incorporate \"any resolution\" on top of Ferret to m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05719","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/2404.05719/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":"2404.05719","created_at":"2026-07-05T08:05:44.613325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05719v1","created_at":"2026-07-05T08:05:44.613325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05719","created_at":"2026-07-05T08:05:44.613325+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5HWUN2I7KEJ","created_at":"2026-07-05T08:05:44.613325+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5HWUN2I7KEJ6YNN","created_at":"2026-07-05T08:05:44.613325+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5HWUN2I","created_at":"2026-07-05T08:05:44.613325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24515","citing_title":"Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29537","citing_title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28646","citing_title":"MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution","ref_index":7,"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":65,"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":37,"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":112,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":129,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ","json":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ.json","graph_json":"https://pith.science/api/pith-number/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/graph.json","events_json":"https://pith.science/api/pith-number/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/events.json","paper":"https://pith.science/paper/Y5HWUN2I"},"agent_actions":{"view_html":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ","download_json":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ.json","view_paper":"https://pith.science/paper/Y5HWUN2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05719&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y5HWUN2I7KEJ6YNNDRINE4Z6SQ/action/replication_record"}},"created_at":"2026-07-05T08:05:44.613325+00:00","updated_at":"2026-07-05T08:05:44.613325+00:00"}