{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BXHKB2CJ3TPL24KMS7YXQJMTAY","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":"2a4e722354cda5312c62307eb0eb578f6370dfd62321df3c4bd56f88b2598946","cross_cats_sorted":["cs.HC","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T13:45:54Z","title_canon_sha256":"c6d5ce9ccc6658442b616ca8a9dd251aec1841ba49931967c4e96a20dd4df2ed"},"schema_version":"1.0","source":{"id":"2105.11941","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11941","created_at":"2026-07-05T04:14:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11941v2","created_at":"2026-07-05T04:14:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11941","created_at":"2026-07-05T04:14:37Z"},{"alias_kind":"pith_short_12","alias_value":"BXHKB2CJ3TPL","created_at":"2026-07-05T04:14:37Z"},{"alias_kind":"pith_short_16","alias_value":"BXHKB2CJ3TPL24KM","created_at":"2026-07-05T04:14:37Z"},{"alias_kind":"pith_short_8","alias_value":"BXHKB2CJ","created_at":"2026-07-05T04:14:37Z"}],"graph_snapshots":[{"event_id":"sha256:f69682cb116367f410dfa2623c8851859921b8e705f50db1fd0d869d0f697f21","target":"graph","created_at":"2026-07-05T04:14:37Z","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/2105.11941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ubiquity of mobile phones makes mobile GUI understanding an important task. Most previous works in this domain require human-created metadata of screens (e.g. View Hierarchy) during inference, which unfortunately is often not available or reliable enough for GUI understanding. Inspired by the impressive success of Transformers in NLP tasks, targeting for purely vision-based GUI understanding, we extend the concepts of Words/Sentence to Pixel-Words/Screen-Sentence, and propose a mobile GUI understanding architecture: Pixel-Words to Screen-Sentence (PW2SS). In analogy to the individual Words","authors_text":"Grayson Hilliard, Jingwen Fu, Sam Yang, Wenjun Zeng, Xiaoyi Zhang, Yuwang Wang","cross_cats":["cs.HC","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T13:45:54Z","title":"Understanding Mobile GUI: from Pixel-Words to Screen-Sentences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11941","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":"sha256:51b84256a68846e375dc23a0322d927ecdced375ba66d7cb4b99ef4476cf4665","target":"record","created_at":"2026-07-05T04:14:37Z","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":"2a4e722354cda5312c62307eb0eb578f6370dfd62321df3c4bd56f88b2598946","cross_cats_sorted":["cs.HC","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T13:45:54Z","title_canon_sha256":"c6d5ce9ccc6658442b616ca8a9dd251aec1841ba49931967c4e96a20dd4df2ed"},"schema_version":"1.0","source":{"id":"2105.11941","kind":"arxiv","version":2}},"canonical_sha256":"0dcea0e849dcdebd714c97f178259306209a1c19b13e796b2d1b95a6ab09c710","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dcea0e849dcdebd714c97f178259306209a1c19b13e796b2d1b95a6ab09c710","first_computed_at":"2026-07-05T04:14:37.551477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:37.551477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2BdDLZ1Dq8lFVOulgp6dDHza8NVePhn8XPIaVAMb/QogGlFrb/L/s7ljO/u4yzGaopr1fW1q1zgqHcWqy2MJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:37.551904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11941","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51b84256a68846e375dc23a0322d927ecdced375ba66d7cb4b99ef4476cf4665","sha256:f69682cb116367f410dfa2623c8851859921b8e705f50db1fd0d869d0f697f21"],"state_sha256":"91a131235b6dc7252d2942f953d5956fda3732b1ac9daa294b59fd00e35aae38"}