{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LHWCONZ27XNAONTVSMJMTQGYTM","short_pith_number":"pith:LHWCONZ2","canonical_record":{"source":{"id":"2411.04890","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T17:28:10Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"9a1da207e32ec36925572e1c2db971345e0195236d7ec5713b619250e193d0ce","abstract_canon_sha256":"48182740c277666eff7905e06eaa76061e5418bee2499cc4ab134224af001ab1"},"schema_version":"1.0"},"canonical_sha256":"59ec27373afdda0736759312c9c0d89b32c4945a5436b1fd086da5b7fd1a2ee2","source":{"kind":"arxiv","id":"2411.04890","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04890","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04890v2","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04890","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"LHWCONZ27XNA","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"LHWCONZ27XNAONTV","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"LHWCONZ2","created_at":"2026-07-05T10:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LHWCONZ27XNAONTVSMJMTQGYTM","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04890","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T17:28:10Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"9a1da207e32ec36925572e1c2db971345e0195236d7ec5713b619250e193d0ce","abstract_canon_sha256":"48182740c277666eff7905e06eaa76061e5418bee2499cc4ab134224af001ab1"},"schema_version":"1.0"},"canonical_sha256":"59ec27373afdda0736759312c9c0d89b32c4945a5436b1fd086da5b7fd1a2ee2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:44.658475Z","signature_b64":"+Nnqx++dk8ufeZczVihXNrbTx7TtNBD9WMbr63TfzmiUO6NdkZYLj/VrUmmPoRRaZNDFA011uB7l6iSwEdRbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59ec27373afdda0736759312c9c0d89b32c4945a5436b1fd086da5b7fd1a2ee2","last_reissued_at":"2026-07-05T10:13:44.657974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:44.657974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04890","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"akhzlnNqvW14eClrGZ52uc8Rou9dn2OfEuOw18aGmYVGR7XHXozDEIT1p/DwHXTbBGXWilCD3xug4nT9i023Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:12:30.651062Z"},"content_sha256":"7122183ec6af96bf49ba71042688eccfc7470b50e86b67b0ac25880850c1cadf","schema_version":"1.0","event_id":"sha256:7122183ec6af96bf49ba71042688eccfc7470b50e86b67b0ac25880850c1cadf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LHWCONZ27XNAONTVSMJMTQGYTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GUI Agents with Foundation Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Bin Wang, Chuhan Wu, Jianye Hao, Jingxuan Chen, Kun Shao, Ruiming Tang, Shuai Wang, Shuai Yu, Weinan Gan, Weiwen Liu, Xingshan Zeng, Xinlong Hao, Yasheng Wang, Yuhan Che, Yuqi Zhou","submitted_at":"2024-11-07T17:28:10Z","abstract_excerpt":"Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), have facilitated the development of intelligent agents capable of performing complex tasks. By leveraging the ability of (M)LLMs to process and interpret Graphical User Interfaces (GUIs), these agents can autonomously execute user instructions, simulating human-like interactions such as clicking and typing. This survey consolidates recent research on (M)LLM-based GUI agents, highlighting key innovations in data resources, frameworks, and applications. We begin by review"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04890","kind":"arxiv","version":2},"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/2411.04890/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":"2026-07-05T10:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5FwQhXhfKiZf5BQGr/Ba6jFdt2VO+hd9igkCZzHv5xooMp+F5Fc7yVasHCFn7WWQPxZUGXww04g3dSHvf/cDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:12:30.652003Z"},"content_sha256":"ec85eaec0a845c0882fefb397573fbddea8418fe96194a43399780c044c21f63","schema_version":"1.0","event_id":"sha256:ec85eaec0a845c0882fefb397573fbddea8418fe96194a43399780c044c21f63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHWCONZ27XNAONTVSMJMTQGYTM/bundle.json","state_url":"https://pith.science/pith/LHWCONZ27XNAONTVSMJMTQGYTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHWCONZ27XNAONTVSMJMTQGYTM/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":"2026-08-05T23:12:30Z","links":{"resolver":"https://pith.science/pith/LHWCONZ27XNAONTVSMJMTQGYTM","bundle":"https://pith.science/pith/LHWCONZ27XNAONTVSMJMTQGYTM/bundle.json","state":"https://pith.science/pith/LHWCONZ27XNAONTVSMJMTQGYTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHWCONZ27XNAONTVSMJMTQGYTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LHWCONZ27XNAONTVSMJMTQGYTM","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":"48182740c277666eff7905e06eaa76061e5418bee2499cc4ab134224af001ab1","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T17:28:10Z","title_canon_sha256":"9a1da207e32ec36925572e1c2db971345e0195236d7ec5713b619250e193d0ce"},"schema_version":"1.0","source":{"id":"2411.04890","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04890","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04890v2","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04890","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"LHWCONZ27XNA","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"LHWCONZ27XNAONTV","created_at":"2026-07-05T10:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"LHWCONZ2","created_at":"2026-07-05T10:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:ec85eaec0a845c0882fefb397573fbddea8418fe96194a43399780c044c21f63","target":"graph","created_at":"2026-07-05T10:13:44Z","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/2411.04890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), have facilitated the development of intelligent agents capable of performing complex tasks. By leveraging the ability of (M)LLMs to process and interpret Graphical User Interfaces (GUIs), these agents can autonomously execute user instructions, simulating human-like interactions such as clicking and typing. This survey consolidates recent research on (M)LLM-based GUI agents, highlighting key innovations in data resources, frameworks, and applications. We begin by review","authors_text":"Bin Wang, Chuhan Wu, Jianye Hao, Jingxuan Chen, Kun Shao, Ruiming Tang, Shuai Wang, Shuai Yu, Weinan Gan, Weiwen Liu, Xingshan Zeng, Xinlong Hao, Yasheng Wang, Yuhan Che, Yuqi Zhou","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T17:28:10Z","title":"GUI Agents with Foundation Models: A Comprehensive Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04890","kind":"arxiv","version":2},"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":"sha256:7122183ec6af96bf49ba71042688eccfc7470b50e86b67b0ac25880850c1cadf","target":"record","created_at":"2026-07-05T10:13:44Z","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":"48182740c277666eff7905e06eaa76061e5418bee2499cc4ab134224af001ab1","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T17:28:10Z","title_canon_sha256":"9a1da207e32ec36925572e1c2db971345e0195236d7ec5713b619250e193d0ce"},"schema_version":"1.0","source":{"id":"2411.04890","kind":"arxiv","version":2}},"canonical_sha256":"59ec27373afdda0736759312c9c0d89b32c4945a5436b1fd086da5b7fd1a2ee2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59ec27373afdda0736759312c9c0d89b32c4945a5436b1fd086da5b7fd1a2ee2","first_computed_at":"2026-07-05T10:13:44.657974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:44.657974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Nnqx++dk8ufeZczVihXNrbTx7TtNBD9WMbr63TfzmiUO6NdkZYLj/VrUmmPoRRaZNDFA011uB7l6iSwEdRbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:44.658475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04890","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7122183ec6af96bf49ba71042688eccfc7470b50e86b67b0ac25880850c1cadf","sha256:ec85eaec0a845c0882fefb397573fbddea8418fe96194a43399780c044c21f63"],"state_sha256":"cab8a7c2d6a098cf08d80be24b15ec9312a886e5b5eda5e5b614bf4f94bc8f00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RF6phLQ14Q6XW65DG5eKLBCNicSgbbx5G4yWelS9F7A41IMGgYOMz3RxilLdbtxcR7JWEAuJ0En3xz/qdmVMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:12:30.658424Z","bundle_sha256":"d51ec7154f473e3b115bfe08b7f76f2a7fbc71684acc851782de86257290d12f"}}