{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F7REUGKKRWHGMDASCNQPA622SZ","short_pith_number":"pith:F7REUGKK","canonical_record":{"source":{"id":"2404.08755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T18:28:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"title_canon_sha256":"15886b73c108318e288386af00f290f18270904061c8182eca3c6526a257a5fc","abstract_canon_sha256":"68a88232d291f8c9c97f065f0bfad3f34bd065a84be6660992c14440ccb375a3"},"schema_version":"1.0"},"canonical_sha256":"2fe24a194a8d8e660c121360f07b5a967eb21860ed86db4050430b2a27dfa4e6","source":{"kind":"arxiv","id":"2404.08755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08755","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08755v1","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08755","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"F7REUGKKRWHG","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"F7REUGKKRWHGMDAS","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"F7REUGKK","created_at":"2026-07-05T08:07:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F7REUGKKRWHGMDASCNQPA622SZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.08755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T18:28:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"title_canon_sha256":"15886b73c108318e288386af00f290f18270904061c8182eca3c6526a257a5fc","abstract_canon_sha256":"68a88232d291f8c9c97f065f0bfad3f34bd065a84be6660992c14440ccb375a3"},"schema_version":"1.0"},"canonical_sha256":"2fe24a194a8d8e660c121360f07b5a967eb21860ed86db4050430b2a27dfa4e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:39.499370Z","signature_b64":"QnS5/iY764Z5zXttpOpggEOyjoXVx88PlcyoRRj1RTpb4iADdVFsYMdGNcjzkfzCt1CFkWh5asbq3Xiz0nHjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe24a194a8d8e660c121360f07b5a967eb21860ed86db4050430b2a27dfa4e6","last_reissued_at":"2026-07-05T08:07:39.498850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:39.498850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.08755","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":"2026-07-05T08:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xcSKEhy7hDXZFOnKEmoO5TzG7LRXFsID3fGtK/MoEyX07MiNZYsljagi2c1PIJC6xDHTiiS9WT3Q1p6oagsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:27.898251Z"},"content_sha256":"b5f3d97c0556d9cfeaedfa80b93e32af13d366b756be1bbba06d6d4a24d5da07","schema_version":"1.0","event_id":"sha256:b5f3d97c0556d9cfeaedfa80b93e32af13d366b756be1bbba06d6d4a24d5da07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F7REUGKKRWHGMDASCNQPA622SZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training a Vision Language Model as Smartphone Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.HC"],"primary_cat":"cs.LG","authors_text":"Ammar Anwar, Janusz Marecki, Nicolai Dorka","submitted_at":"2024-04-12T18:28:44Z","abstract_excerpt":"Addressing the challenge of a digital assistant capable of executing a wide array of user tasks, our research focuses on the realm of instruction-based mobile device control. We leverage recent advancements in large language models (LLMs) and present a visual language model (VLM) that can fulfill diverse tasks on mobile devices. Our model functions by interacting solely with the user interface (UI). It uses the visual input from the device screen and mimics human-like interactions, encompassing gestures such as tapping and swiping. This generality in the input and output space allows our agent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08755","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/2404.08755/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":"2026-07-05T08:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PV6ajUfqW8smbQRi3CFg0F+PhQuxel/Z94UmIQM3FXbGt4MxdAZaA94i8o75xSpjQ5Br6EIfQ6c9bgrkgMJOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:27.898731Z"},"content_sha256":"bee11dc04307cedc3bfd0c87b6fb509e01f5abae52fd6f9410ad30c3656e1b40","schema_version":"1.0","event_id":"sha256:bee11dc04307cedc3bfd0c87b6fb509e01f5abae52fd6f9410ad30c3656e1b40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/bundle.json","state_url":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7REUGKKRWHGMDASCNQPA622SZ/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":"2026-07-09T04:32:27Z","links":{"resolver":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ","bundle":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/bundle.json","state":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7REUGKKRWHGMDASCNQPA622SZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F7REUGKKRWHGMDASCNQPA622SZ","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":"68a88232d291f8c9c97f065f0bfad3f34bd065a84be6660992c14440ccb375a3","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T18:28:44Z","title_canon_sha256":"15886b73c108318e288386af00f290f18270904061c8182eca3c6526a257a5fc"},"schema_version":"1.0","source":{"id":"2404.08755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08755","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08755v1","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08755","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"F7REUGKKRWHG","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"F7REUGKKRWHGMDAS","created_at":"2026-07-05T08:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"F7REUGKK","created_at":"2026-07-05T08:07:39Z"}],"graph_snapshots":[{"event_id":"sha256:bee11dc04307cedc3bfd0c87b6fb509e01f5abae52fd6f9410ad30c3656e1b40","target":"graph","created_at":"2026-07-05T08:07:39Z","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/2404.08755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Addressing the challenge of a digital assistant capable of executing a wide array of user tasks, our research focuses on the realm of instruction-based mobile device control. We leverage recent advancements in large language models (LLMs) and present a visual language model (VLM) that can fulfill diverse tasks on mobile devices. Our model functions by interacting solely with the user interface (UI). It uses the visual input from the device screen and mimics human-like interactions, encompassing gestures such as tapping and swiping. This generality in the input and output space allows our agent","authors_text":"Ammar Anwar, Janusz Marecki, Nicolai Dorka","cross_cats":["cs.AI","cs.CV","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T18:28:44Z","title":"Training a Vision Language Model as Smartphone Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08755","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:b5f3d97c0556d9cfeaedfa80b93e32af13d366b756be1bbba06d6d4a24d5da07","target":"record","created_at":"2026-07-05T08:07:39Z","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":"68a88232d291f8c9c97f065f0bfad3f34bd065a84be6660992c14440ccb375a3","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T18:28:44Z","title_canon_sha256":"15886b73c108318e288386af00f290f18270904061c8182eca3c6526a257a5fc"},"schema_version":"1.0","source":{"id":"2404.08755","kind":"arxiv","version":1}},"canonical_sha256":"2fe24a194a8d8e660c121360f07b5a967eb21860ed86db4050430b2a27dfa4e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fe24a194a8d8e660c121360f07b5a967eb21860ed86db4050430b2a27dfa4e6","first_computed_at":"2026-07-05T08:07:39.498850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:39.498850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnS5/iY764Z5zXttpOpggEOyjoXVx88PlcyoRRj1RTpb4iADdVFsYMdGNcjzkfzCt1CFkWh5asbq3Xiz0nHjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:39.499370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5f3d97c0556d9cfeaedfa80b93e32af13d366b756be1bbba06d6d4a24d5da07","sha256:bee11dc04307cedc3bfd0c87b6fb509e01f5abae52fd6f9410ad30c3656e1b40"],"state_sha256":"7389cd3b8581f3e1f3ebcb9ecd1a6dc82ff5e071eb31b1dc3ea538336b6b12d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dafzGjF3Xadx03sSH+UhfBIeJpAtiDNNhlNwQcJ4kNKUdGEAMErL4hINqbH0xBfFsySnyzLoaj1LtNcRpMeoCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:32:27.903547Z","bundle_sha256":"68a0e2e3cb8ec144483324e8c6f651625e6a8020cd638998bf587618efa13b08"}}