{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SWB3SLGEOZBK2N4A3B2BKA6H5Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5322677ed9934a592033fc71a9739494f276cba6ff69a11c14cfcdceadf94f22","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:53:37Z","title_canon_sha256":"a4d4f19a887cbad7c99a8613bb54bf620ada14afc4928d6f3bb01ed591098282"},"schema_version":"1.0","source":{"id":"2311.07562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07562","created_at":"2026-07-05T07:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07562v1","created_at":"2026-07-05T07:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07562","created_at":"2026-07-05T07:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"SWB3SLGEOZBK","created_at":"2026-07-05T07:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"SWB3SLGEOZBK2N4A","created_at":"2026-07-05T07:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"SWB3SLGE","created_at":"2026-07-05T07:12:13Z"}],"graph_snapshots":[{"event_id":"sha256:80e32f3be81f22e08f3b84e20490c5a4efc66f6f89df259ecca4f612899e83aa","target":"graph","created_at":"2026-07-05T07:12:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.07562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MM-Navigator, a GPT-4V-based agent for the smartphone graphical user interface (GUI) navigation task. MM-Navigator can interact with a smartphone screen as human users, and determine subsequent actions to fulfill given instructions. Our findings demonstrate that large multimodal models (LMMs), specifically GPT-4V, excel in zero-shot GUI navigation through its advanced screen interpretation, action reasoning, and precise action localization capabilities. We first benchmark MM-Navigator on our collected iOS screen dataset. According to human assessments, the system exhibited a 91\\% ac","authors_text":"An Yan, Jianfeng Gao, Jianfeng Wang, Jianwei Yang, Julian McAuley, Kevin Lin, Lijuan Wang, Linjie Li, Wanrong Zhu, Yiwu Zhong, Zhengyuan Yang, Zicheng Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:53:37Z","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07562","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a5a65c070b6baa9c8db129bd2ff218a2efdbeeafe3d4f03c3abe86d5a8f01b8d","target":"record","created_at":"2026-07-05T07:12:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5322677ed9934a592033fc71a9739494f276cba6ff69a11c14cfcdceadf94f22","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:53:37Z","title_canon_sha256":"a4d4f19a887cbad7c99a8613bb54bf620ada14afc4928d6f3bb01ed591098282"},"schema_version":"1.0","source":{"id":"2311.07562","kind":"arxiv","version":1}},"canonical_sha256":"9583b92cc47642ad3780d8741503c7ee7b3e53c0b6cc349bafab65c25995ffcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9583b92cc47642ad3780d8741503c7ee7b3e53c0b6cc349bafab65c25995ffcf","first_computed_at":"2026-07-05T07:12:13.939268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:13.939268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PuKi4ZtZKXREiGrbGyvlNzcsuXgAYJSR+k43kBL1ClYQLGsz7SZAzIXt2rgVcqn0nczj0rRBOTjqIpcPLcqHCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:13.939751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5a65c070b6baa9c8db129bd2ff218a2efdbeeafe3d4f03c3abe86d5a8f01b8d","sha256:80e32f3be81f22e08f3b84e20490c5a4efc66f6f89df259ecca4f612899e83aa"],"state_sha256":"8fe282f5323ed4bca482dce5ae8dcc37b93d121f2c76ca3aee36e1fbce3af415"}