{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PKD6Q5MF7GHVLD4NUK3U5XAY4W","short_pith_number":"pith:PKD6Q5MF","schema_version":"1.0","canonical_sha256":"7a87e87585f98f558f8da2b74edc18e5bc75c4085e0827e36a8dba1e6d6b72b4","source":{"kind":"arxiv","id":"2504.13936","version":2},"attestation_state":"computed","paper":{"title":"ViMo: A Generative Visual GUI World Model for App Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.HC","authors_text":"Bohan Tang, Dezhao Luo, Georgios Papoudakis, Jianye Hao, Jifei Song, Jun Wang, Kang Li, Kun Shao, Shaogang Gong","submitted_at":"2025-04-15T14:03:10Z","abstract_excerpt":"App agents, which autonomously operate mobile Apps through Graphical User Interfaces (GUIs), have gained significant interest in real-world applications. Yet, they often struggle with long-horizon planning, failing to find the optimal actions for complex tasks with longer steps. To address this, world models are used to predict the next GUI observation based on user actions, enabling more effective agent planning. However, existing world models primarily focus on generating only textual descriptions, lacking essential visual details. To fill this gap, we propose ViMo, the first visual world mo"},"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":"2504.13936","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:03:10Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"a4ba2a4c38035b8020c53bc5d2d94d76fa3f1d588f4956ded9d790cac2ed3c2a","abstract_canon_sha256":"b515ba8337887025e508445027192b39ffeff0bc22b46b4b29715001f05b88df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:43.268021Z","signature_b64":"FfMetrCwrKqnpvJMJTikDRmS74yBEViUkK4ZH+phMto9rwSN/VBWW8FF4J0vRE5mOSJvxqotHLI3/AbXdXKtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a87e87585f98f558f8da2b74edc18e5bc75c4085e0827e36a8dba1e6d6b72b4","last_reissued_at":"2026-07-05T11:05:43.267566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:43.267566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViMo: A Generative Visual GUI World Model for App Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.HC","authors_text":"Bohan Tang, Dezhao Luo, Georgios Papoudakis, Jianye Hao, Jifei Song, Jun Wang, Kang Li, Kun Shao, Shaogang Gong","submitted_at":"2025-04-15T14:03:10Z","abstract_excerpt":"App agents, which autonomously operate mobile Apps through Graphical User Interfaces (GUIs), have gained significant interest in real-world applications. Yet, they often struggle with long-horizon planning, failing to find the optimal actions for complex tasks with longer steps. To address this, world models are used to predict the next GUI observation based on user actions, enabling more effective agent planning. However, existing world models primarily focus on generating only textual descriptions, lacking essential visual details. To fill this gap, we propose ViMo, the first visual world mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13936","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/2504.13936/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":"2504.13936","created_at":"2026-07-05T11:05:43.267631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13936v2","created_at":"2026-07-05T11:05:43.267631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13936","created_at":"2026-07-05T11:05:43.267631+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKD6Q5MF7GHV","created_at":"2026-07-05T11:05:43.267631+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKD6Q5MF7GHVLD4N","created_at":"2026-07-05T11:05:43.267631+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKD6Q5MF","created_at":"2026-07-05T11:05:43.267631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":256,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11078","citing_title":"A History-Aware Visually Grounded Critic for Computer Use Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04627","citing_title":"MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14311","citing_title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02345","citing_title":"UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14311","citing_title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":256,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10866","citing_title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W","json":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W.json","graph_json":"https://pith.science/api/pith-number/PKD6Q5MF7GHVLD4NUK3U5XAY4W/graph.json","events_json":"https://pith.science/api/pith-number/PKD6Q5MF7GHVLD4NUK3U5XAY4W/events.json","paper":"https://pith.science/paper/PKD6Q5MF"},"agent_actions":{"view_html":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W","download_json":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W.json","view_paper":"https://pith.science/paper/PKD6Q5MF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13936&json=true","fetch_graph":"https://pith.science/api/pith-number/PKD6Q5MF7GHVLD4NUK3U5XAY4W/graph.json","fetch_events":"https://pith.science/api/pith-number/PKD6Q5MF7GHVLD4NUK3U5XAY4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/action/storage_attestation","attest_author":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/action/author_attestation","sign_citation":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/action/citation_signature","submit_replication":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/action/replication_record"}},"created_at":"2026-07-05T11:05:43.267631+00:00","updated_at":"2026-07-05T11:05:43.267631+00:00"}