{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F7REUGKKRWHGMDASCNQPA622SZ","short_pith_number":"pith:F7REUGKK","schema_version":"1.0","canonical_sha256":"2fe24a194a8d8e660c121360f07b5a967eb21860ed86db4050430b2a27dfa4e6","source":{"kind":"arxiv","id":"2404.08755","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.08755","created_at":"2026-07-05T08:07:39.498909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08755v1","created_at":"2026-07-05T08:07:39.498909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08755","created_at":"2026-07-05T08:07:39.498909+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7REUGKKRWHG","created_at":"2026-07-05T08:07:39.498909+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7REUGKKRWHGMDAS","created_at":"2026-07-05T08:07:39.498909+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7REUGKK","created_at":"2026-07-05T08:07:39.498909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ","json":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ.json","graph_json":"https://pith.science/api/pith-number/F7REUGKKRWHGMDASCNQPA622SZ/graph.json","events_json":"https://pith.science/api/pith-number/F7REUGKKRWHGMDASCNQPA622SZ/events.json","paper":"https://pith.science/paper/F7REUGKK"},"agent_actions":{"view_html":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ","download_json":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ.json","view_paper":"https://pith.science/paper/F7REUGKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08755&json=true","fetch_graph":"https://pith.science/api/pith-number/F7REUGKKRWHGMDASCNQPA622SZ/graph.json","fetch_events":"https://pith.science/api/pith-number/F7REUGKKRWHGMDASCNQPA622SZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/action/storage_attestation","attest_author":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/action/author_attestation","sign_citation":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/action/citation_signature","submit_replication":"https://pith.science/pith/F7REUGKKRWHGMDASCNQPA622SZ/action/replication_record"}},"created_at":"2026-07-05T08:07:39.498909+00:00","updated_at":"2026-07-05T08:07:39.498909+00:00"}