{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VNDETRNUMWYHW7WX2KHXUTMRWD","short_pith_number":"pith:VNDETRNU","schema_version":"1.0","canonical_sha256":"ab4649c5b465b07b7ed7d28f7a4d91b0e0c57b1e6be857e71cd48649d2a8c619","source":{"kind":"arxiv","id":"2203.07828","version":1},"attestation_state":"computed","paper":{"title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Taichi Iki","submitted_at":"2022-03-15T12:32:28Z","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 "},"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":"2203.07828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T12:32:28Z","cross_cats_sorted":[],"title_canon_sha256":"79d29460a165916002326b58f2009ae62b9c4dfb77fcd7e53c310082d9c87f41","abstract_canon_sha256":"d67efad91d8ff6252866a99fc0a9fd8e77492f89d6fcb6a1ab7454ba4326d633"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:23.096598Z","signature_b64":"WxmLCwrlctfTeeofVQ1oOYmi8vQ90U5MoI5g51lt8j1LnfERKgXuS9B3PxsnW9/lma3J9E3COgy8Y06AHB0hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab4649c5b465b07b7ed7d28f7a4d91b0e0c57b1e6be857e71cd48649d2a8c619","last_reissued_at":"2026-07-05T04:05:23.096092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:23.096092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Taichi Iki","submitted_at":"2022-03-15T12:32:28Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07828","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/2203.07828/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":"2203.07828","created_at":"2026-07-05T04:05:23.096149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07828v1","created_at":"2026-07-05T04:05:23.096149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07828","created_at":"2026-07-05T04:05:23.096149+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNDETRNUMWYH","created_at":"2026-07-05T04:05:23.096149+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNDETRNUMWYHW7WX","created_at":"2026-07-05T04:05:23.096149+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNDETRNU","created_at":"2026-07-05T04:05:23.096149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":65,"is_internal_anchor":false},{"citing_arxiv_id":"2303.17491","citing_title":"Language Models can Solve Computer Tasks","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD","json":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD.json","graph_json":"https://pith.science/api/pith-number/VNDETRNUMWYHW7WX2KHXUTMRWD/graph.json","events_json":"https://pith.science/api/pith-number/VNDETRNUMWYHW7WX2KHXUTMRWD/events.json","paper":"https://pith.science/paper/VNDETRNU"},"agent_actions":{"view_html":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD","download_json":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD.json","view_paper":"https://pith.science/paper/VNDETRNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07828&json=true","fetch_graph":"https://pith.science/api/pith-number/VNDETRNUMWYHW7WX2KHXUTMRWD/graph.json","fetch_events":"https://pith.science/api/pith-number/VNDETRNUMWYHW7WX2KHXUTMRWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD/action/storage_attestation","attest_author":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD/action/author_attestation","sign_citation":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD/action/citation_signature","submit_replication":"https://pith.science/pith/VNDETRNUMWYHW7WX2KHXUTMRWD/action/replication_record"}},"created_at":"2026-07-05T04:05:23.096149+00:00","updated_at":"2026-07-05T04:05:23.096149+00:00"}