{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PKD6Q5MF7GHVLD4NUK3U5XAY4W","short_pith_number":"pith:PKD6Q5MF","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"},"canonical_sha256":"7a87e87585f98f558f8da2b74edc18e5bc75c4085e0827e36a8dba1e6d6b72b4","source":{"kind":"arxiv","id":"2504.13936","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13936","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13936v2","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13936","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"PKD6Q5MF7GHV","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"PKD6Q5MF7GHVLD4N","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"PKD6Q5MF","created_at":"2026-07-05T11:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PKD6Q5MF7GHVLD4NUK3U5XAY4W","target":"record","payload":{"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"},"canonical_sha256":"7a87e87585f98f558f8da2b74edc18e5bc75c4085e0827e36a8dba1e6d6b72b4","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"},"source_kind":"arxiv","source_id":"2504.13936","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":"2026-07-05T11:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nL9rwwsDVbjk98nDgyYvuKCNLe3fhDX+eSzEmxDkSrde6M1mBVdF323rK3OgvFtrbezXbVRtVC5H7+nMfDMyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:21:31.712604Z"},"content_sha256":"1732d99a7190bff50b49568f38206e48d9df02fcc40a2c60ec51a2951cce3019","schema_version":"1.0","event_id":"sha256:1732d99a7190bff50b49568f38206e48d9df02fcc40a2c60ec51a2951cce3019"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PKD6Q5MF7GHVLD4NUK3U5XAY4W","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFDWk6txDXd2s7nVfeWuwufOohy2XR+5oqvPV4kYd/NhowTPIChjZk99X1ku1uEjuXHeZ0pShnSHjtV2+p5UDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:21:31.713635Z"},"content_sha256":"9499aa08ccb657a24bdd39b8cc6959de834757ab8a6982d381ea176b3ad7a7f6","schema_version":"1.0","event_id":"sha256:9499aa08ccb657a24bdd39b8cc6959de834757ab8a6982d381ea176b3ad7a7f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/bundle.json","state_url":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/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":"2026-08-04T23:21:31Z","links":{"resolver":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W","bundle":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/bundle.json","state":"https://pith.science/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PKD6Q5MF7GHVLD4NUK3U5XAY4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PKD6Q5MF7GHVLD4NUK3U5XAY4W","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":"b515ba8337887025e508445027192b39ffeff0bc22b46b4b29715001f05b88df","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:03:10Z","title_canon_sha256":"a4ba2a4c38035b8020c53bc5d2d94d76fa3f1d588f4956ded9d790cac2ed3c2a"},"schema_version":"1.0","source":{"id":"2504.13936","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13936","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13936v2","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13936","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"PKD6Q5MF7GHV","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"PKD6Q5MF7GHVLD4N","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"PKD6Q5MF","created_at":"2026-07-05T11:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:9499aa08ccb657a24bdd39b8cc6959de834757ab8a6982d381ea176b3ad7a7f6","target":"graph","created_at":"2026-07-05T11:05:43Z","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/2504.13936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bohan Tang, Dezhao Luo, Georgios Papoudakis, Jianye Hao, Jifei Song, Jun Wang, Kang Li, Kun Shao, Shaogang Gong","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:03:10Z","title":"ViMo: A Generative Visual GUI World Model for App Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13936","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":"sha256:1732d99a7190bff50b49568f38206e48d9df02fcc40a2c60ec51a2951cce3019","target":"record","created_at":"2026-07-05T11:05:43Z","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":"b515ba8337887025e508445027192b39ffeff0bc22b46b4b29715001f05b88df","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:03:10Z","title_canon_sha256":"a4ba2a4c38035b8020c53bc5d2d94d76fa3f1d588f4956ded9d790cac2ed3c2a"},"schema_version":"1.0","source":{"id":"2504.13936","kind":"arxiv","version":2}},"canonical_sha256":"7a87e87585f98f558f8da2b74edc18e5bc75c4085e0827e36a8dba1e6d6b72b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a87e87585f98f558f8da2b74edc18e5bc75c4085e0827e36a8dba1e6d6b72b4","first_computed_at":"2026-07-05T11:05:43.267566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:43.267566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FfMetrCwrKqnpvJMJTikDRmS74yBEViUkK4ZH+phMto9rwSN/VBWW8FF4J0vRE5mOSJvxqotHLI3/AbXdXKtAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:43.268021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13936","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1732d99a7190bff50b49568f38206e48d9df02fcc40a2c60ec51a2951cce3019","sha256:9499aa08ccb657a24bdd39b8cc6959de834757ab8a6982d381ea176b3ad7a7f6"],"state_sha256":"8af0f54ddefef762c7c33776f87ee109e5a70093624b469b093663d97c02e68e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XjcEpiOkygBztv3z/+zJizJ/bmWfQUG2wrkOIeYiV7gpLKQNSpLKh2MIUaxJ6x9/bcjeeIyKBPqFt7NyySZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:21:31.719070Z","bundle_sha256":"c29583973dc245081c1b7d2d737a246d76f70eff4a8bf2ab14fdba2744aff6b7"}}