{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SWB3SLGEOZBK2N4A3B2BKA6H5Z","short_pith_number":"pith:SWB3SLGE","canonical_record":{"source":{"id":"2311.07562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:53:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4d4f19a887cbad7c99a8613bb54bf620ada14afc4928d6f3bb01ed591098282","abstract_canon_sha256":"5322677ed9934a592033fc71a9739494f276cba6ff69a11c14cfcdceadf94f22"},"schema_version":"1.0"},"canonical_sha256":"9583b92cc47642ad3780d8741503c7ee7b3e53c0b6cc349bafab65c25995ffcf","source":{"kind":"arxiv","id":"2311.07562","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SWB3SLGEOZBK2N4A3B2BKA6H5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:53:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4d4f19a887cbad7c99a8613bb54bf620ada14afc4928d6f3bb01ed591098282","abstract_canon_sha256":"5322677ed9934a592033fc71a9739494f276cba6ff69a11c14cfcdceadf94f22"},"schema_version":"1.0"},"canonical_sha256":"9583b92cc47642ad3780d8741503c7ee7b3e53c0b6cc349bafab65c25995ffcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:13.939751Z","signature_b64":"PuKi4ZtZKXREiGrbGyvlNzcsuXgAYJSR+k43kBL1ClYQLGsz7SZAzIXt2rgVcqn0nczj0rRBOTjqIpcPLcqHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9583b92cc47642ad3780d8741503c7ee7b3e53c0b6cc349bafab65c25995ffcf","last_reissued_at":"2026-07-05T07:12:13.939268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:13.939268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07562","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:12:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFfnT4nL8GsEdoDfY38m4HWsMWgP30dclcouRbgRQVyYmkE0MnZdbl8I2/QRFfWh1Yju39xrh4pFy23qkTTxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:12:58.878987Z"},"content_sha256":"a5a65c070b6baa9c8db129bd2ff218a2efdbeeafe3d4f03c3abe86d5a8f01b8d","schema_version":"1.0","event_id":"sha256:a5a65c070b6baa9c8db129bd2ff218a2efdbeeafe3d4f03c3abe86d5a8f01b8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SWB3SLGEOZBK2N4A3B2BKA6H5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2023-11-13T18:53:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07562","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/2311.07562/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:12:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jHz/YWZY9SBhabGMJwEdq553ZnKRdXyz789QmVqQJ4AVjNGjmAHZ5FizuiEW81ctwbN4GE30yjv3XkOtj9/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:12:58.879513Z"},"content_sha256":"80e32f3be81f22e08f3b84e20490c5a4efc66f6f89df259ecca4f612899e83aa","schema_version":"1.0","event_id":"sha256:80e32f3be81f22e08f3b84e20490c5a4efc66f6f89df259ecca4f612899e83aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z/bundle.json","state_url":"https://pith.science/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T07:12:58Z","links":{"resolver":"https://pith.science/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z","bundle":"https://pith.science/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z/bundle.json","state":"https://pith.science/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWB3SLGEOZBK2N4A3B2BKA6H5Z/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5luX2aF93cvHBxB/ygzBFPklCZyWZvIvOJAoyvUREgwuwFCkiP7dT//Yd48qGy8luaAEeOo2pSyXdzfjggifAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:12:58.884785Z","bundle_sha256":"96eba625787cd341678960e76b07bacfe8bfda4f23bb470ff825aba111d46715"}}