{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VNDETRNUMWYHW7WX2KHXUTMRWD","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":"d67efad91d8ff6252866a99fc0a9fd8e77492f89d6fcb6a1ab7454ba4326d633","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T12:32:28Z","title_canon_sha256":"79d29460a165916002326b58f2009ae62b9c4dfb77fcd7e53c310082d9c87f41"},"schema_version":"1.0","source":{"id":"2203.07828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.07828","created_at":"2026-07-05T04:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2203.07828v1","created_at":"2026-07-05T04:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07828","created_at":"2026-07-05T04:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"VNDETRNUMWYH","created_at":"2026-07-05T04:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"VNDETRNUMWYHW7WX","created_at":"2026-07-05T04:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"VNDETRNU","created_at":"2026-07-05T04:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:c0e7867790ca1819cf1ee2c1f94bb270b0e2f972871dfdb9881a561dc8c6d873","target":"graph","created_at":"2026-07-05T04:05:23Z","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/2203.07828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Transformers are good foundations for unified multi-task models owing to their task-agnostic representation. Pre-trained Transformers are often combined with text-to-text framework to execute multiple tasks by a single model. Performing a task through a graphical user interface (GUI) is another candidate to accommodate various tasks, including multi-step tasks with vision and language inputs. However, few papers combine pre-trained Transformers with performing through GUI. To fill this gap, we explore a framework in which a model performs a task by manipulating the GUI implemented ","authors_text":"Akiko Aizawa, Taichi Iki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T12:32:28Z","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07828","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:eeb06e25e800a243f5f2f39851084e20f894b69646ad3c57222da248ec91b106","target":"record","created_at":"2026-07-05T04:05:23Z","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":"d67efad91d8ff6252866a99fc0a9fd8e77492f89d6fcb6a1ab7454ba4326d633","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T12:32:28Z","title_canon_sha256":"79d29460a165916002326b58f2009ae62b9c4dfb77fcd7e53c310082d9c87f41"},"schema_version":"1.0","source":{"id":"2203.07828","kind":"arxiv","version":1}},"canonical_sha256":"ab4649c5b465b07b7ed7d28f7a4d91b0e0c57b1e6be857e71cd48649d2a8c619","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab4649c5b465b07b7ed7d28f7a4d91b0e0c57b1e6be857e71cd48649d2a8c619","first_computed_at":"2026-07-05T04:05:23.096092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:23.096092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WxmLCwrlctfTeeofVQ1oOYmi8vQ90U5MoI5g51lt8j1LnfERKgXuS9B3PxsnW9/lma3J9E3COgy8Y06AHB0hAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:23.096598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.07828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb06e25e800a243f5f2f39851084e20f894b69646ad3c57222da248ec91b106","sha256:c0e7867790ca1819cf1ee2c1f94bb270b0e2f972871dfdb9881a561dc8c6d873"],"state_sha256":"e05807d7dc2e8c39137f446805f7ad7738c296e560f08d63ddd847219ecccffd"}