{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NLIXKHKPME3NHIOJQ4YVW5FPMV","short_pith_number":"pith:NLIXKHKP","canonical_record":{"source":{"id":"2312.13771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"4af3c8c63187b7042d09f7707a621ba4ff661c5067efaa5e0c6ce20838930e23","abstract_canon_sha256":"9a32a980081b8d77ebaf7885933ae6cda5952055956415891cc187a99082d678"},"schema_version":"1.0"},"canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","source":{"kind":"arxiv","id":"2312.13771","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13771","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13771v2","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13771","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"NLIXKHKPME3N","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NLIXKHKPME3NHIOJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NLIXKHKP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NLIXKHKPME3NHIOJQ4YVW5FPMV","target":"record","payload":{"canonical_record":{"source":{"id":"2312.13771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"4af3c8c63187b7042d09f7707a621ba4ff661c5067efaa5e0c6ce20838930e23","abstract_canon_sha256":"9a32a980081b8d77ebaf7885933ae6cda5952055956415891cc187a99082d678"},"schema_version":"1.0"},"canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.406386Z","signature_b64":"QGz84h7qlYfPuGlhpfUtNkid7k19mSKKZxx856DGBeG7kSEVLP1dURPiV7pCzHK7AnTBZjYSAARImJqxvGh6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","last_reissued_at":"2026-05-17T23:38:14.405660Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.405660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.13771","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":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PirRIazgU2wImQX5wphb0afBMMOR36EjcWKrjud9U3yh7TZ9jS2TTH+xowpkLlleJh5jDrAdTK/OcMlEAuSxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:17:55.281591Z"},"content_sha256":"8535499aa31433ecfa0ec46db2779f84aa7f04dd4ad78e26d15b868eab6744b0","schema_version":"1.0","event_id":"sha256:8535499aa31433ecfa0ec46db2779f84aa7f04dd4ad78e26d15b868eab6744b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NLIXKHKPME3NHIOJQ4YVW5FPMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AppAgent: Multimodal Agents as Smartphone Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Chi Zhang, Gang Yu, Jiaxuan Liu, Xin Chen, Yucheng Han, Zebiao Huang, Zhao Yang","submitted_at":"2023-12-21T11:52:45Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The agent can reliably learn to navigate and execute tasks in new apps through autonomous exploration or human demonstrations, producing a knowledge base that generalizes across applications.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"e0d601a309ea2d10bf0cc1852192cc740bdfac984662b4a09ca1aa64d75b0176"},"source":{"id":"2312.13771","kind":"arxiv","version":2},"verdict":{"id":"8c086a79-6616-4ce5-893d-c4daba15993a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T10:10:48.536796Z","strongest_claim":"Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps.","one_line_summary":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The agent can reliably learn to navigate and execute tasks in new apps through autonomous exploration or human demonstrations, producing a knowledge base that generalizes across applications.","pith_extraction_headline":""},"references":{"count":286,"sample":[{"doi":"","year":2022,"title":"Meta FAIR, Anton Bakhtin, Noam Brown, Emily Dinan, Gabriele Farina, Colin Flaherty, Daniel Fried, Andrew Goff, Jonathan Gray, Hengyuan Hu, et al. 2022. Human-level play in the game of diplomacy by com","work_id":"1ceb4a39-65c8-410c-9767-2ac7b120f2e8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Multimodal web navigation with instruction-finetuned foundation models","work_id":"0f8b8630-9215-4cb8-9b7d-e58e6b1f7bbb","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","work_id":"0915d1fc-bc46-4128-871e-f9233dca44b6","ref_index":7,"cited_arxiv_id":"2307.12856","is_internal_anchor":true},{"doi":"","year":2023,"title":"Chartllama: A multimodal llm for chart understanding and generation","work_id":"f6c4f1ff-0ce7-47e8-82e5-5c24c2a3ed9f","ref_index":8,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","ref_index":9,"cited_arxiv_id":"2308.00352","is_internal_anchor":true}],"resolved_work":286,"snapshot_sha256":"885821595754b102708f214ad9e2814c5947fa18007c701fd0328ce61111a172","internal_anchors":19},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f5de55fee7c9bea80b8fbbb1c74c2316415b5a18f619b190dd3414e0f92b7942"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"8c086a79-6616-4ce5-893d-c4daba15993a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERFOkkkiQbpZ0bjOrHr4dW4v+CVMU4c7Fhn8w4Rlr+H4nYSekU4JevFzbQOQgYYrNyrD5aSP5Y4BogZUYzqiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:17:55.282679Z"},"content_sha256":"6f8d0ff2ffa467118a63610c3e7a9710d27205d8f3491f49e1a9d579091f6783","schema_version":"1.0","event_id":"sha256:6f8d0ff2ffa467118a63610c3e7a9710d27205d8f3491f49e1a9d579091f6783"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/bundle.json","state_url":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/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":"2026-05-30T13:17:55Z","links":{"resolver":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV","bundle":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/bundle.json","state":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NLIXKHKPME3NHIOJQ4YVW5FPMV","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":"9a32a980081b8d77ebaf7885933ae6cda5952055956415891cc187a99082d678","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:52:45Z","title_canon_sha256":"4af3c8c63187b7042d09f7707a621ba4ff661c5067efaa5e0c6ce20838930e23"},"schema_version":"1.0","source":{"id":"2312.13771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13771","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13771v2","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13771","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"NLIXKHKPME3N","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NLIXKHKPME3NHIOJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NLIXKHKP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6f8d0ff2ffa467118a63610c3e7a9710d27205d8f3491f49e1a9d579091f6783","target":"graph","created_at":"2026-05-17T23:38:14Z","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":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The agent can reliably learn to navigate and execute tasks in new apps through autonomous exploration or human demonstrations, producing a knowledge base that generalizes across applications."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations."}],"snapshot_sha256":"e0d601a309ea2d10bf0cc1852192cc740bdfac984662b4a09ca1aa64d75b0176"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f5de55fee7c9bea80b8fbbb1c74c2316415b5a18f619b190dd3414e0f92b7942"},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning","authors_text":"Bin Fu, Chi Zhang, Gang Yu, Jiaxuan Liu, Xin Chen, Yucheng Han, Zebiao Huang, Zhao Yang","cross_cats":[],"headline":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:52:45Z","title":"AppAgent: Multimodal Agents as Smartphone Users"},"references":{"count":286,"internal_anchors":19,"resolved_work":286,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Meta FAIR, Anton Bakhtin, Noam Brown, Emily Dinan, Gabriele Farina, Colin Flaherty, Daniel Fried, Andrew Goff, Jonathan Gray, Hengyuan Hu, et al. 2022. Human-level play in the game of diplomacy by com","work_id":"1ceb4a39-65c8-410c-9767-2ac7b120f2e8","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"title":"Multimodal web navigation with instruction-finetuned foundation models","work_id":"0f8b8630-9215-4cb8-9b7d-e58e6b1f7bbb","year":2023},{"cited_arxiv_id":"2307.12856","doi":"","is_internal_anchor":true,"ref_index":7,"title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","work_id":"0915d1fc-bc46-4128-871e-f9233dca44b6","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":8,"title":"Chartllama: A multimodal llm for chart understanding and generation","work_id":"f6c4f1ff-0ce7-47e8-82e5-5c24c2a3ed9f","year":2023},{"cited_arxiv_id":"2308.00352","doi":"","is_internal_anchor":true,"ref_index":9,"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","year":2023}],"snapshot_sha256":"885821595754b102708f214ad9e2814c5947fa18007c701fd0328ce61111a172"},"source":{"id":"2312.13771","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T10:10:48.536796Z","id":"8c086a79-6616-4ce5-893d-c4daba15993a","model_set":{"reader":"grok-4.3"},"one_line_summary":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"","strongest_claim":"Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps.","weakest_assumption":"The agent can reliably learn to navigate and execute tasks in new apps through autonomous exploration or human demonstrations, producing a knowledge base that generalizes across applications."}},"verdict_id":"8c086a79-6616-4ce5-893d-c4daba15993a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8535499aa31433ecfa0ec46db2779f84aa7f04dd4ad78e26d15b868eab6744b0","target":"record","created_at":"2026-05-17T23:38:14Z","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":"9a32a980081b8d77ebaf7885933ae6cda5952055956415891cc187a99082d678","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:52:45Z","title_canon_sha256":"4af3c8c63187b7042d09f7707a621ba4ff661c5067efaa5e0c6ce20838930e23"},"schema_version":"1.0","source":{"id":"2312.13771","kind":"arxiv","version":2}},"canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","first_computed_at":"2026-05-17T23:38:14.405660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:14.405660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QGz84h7qlYfPuGlhpfUtNkid7k19mSKKZxx856DGBeG7kSEVLP1dURPiV7pCzHK7AnTBZjYSAARImJqxvGh6Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:14.406386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8535499aa31433ecfa0ec46db2779f84aa7f04dd4ad78e26d15b868eab6744b0","sha256:6f8d0ff2ffa467118a63610c3e7a9710d27205d8f3491f49e1a9d579091f6783"],"state_sha256":"565727e3e713835bc6519b53c9fa29f974f401426292be7d3befb919fcc25ae6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DOQjlTpXTGiL0Ud5VASQUTMNUs4+6SwDR02SaXSdyOnO0eusZ7MiQ+pCOM7FznIviUOL4ohXsluoiQ+/GPCJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:17:55.287223Z","bundle_sha256":"ffb77a72a803edcf15e915e00bfc9df77aa2d5860a96f0e3dae3d7b4a77b5aa7"}}