{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H2VE2L3UTFKZLHWE6IIFECNCZ2","short_pith_number":"pith:H2VE2L3U","schema_version":"1.0","canonical_sha256":"3eaa4d2f749955959ec4f2105209a2ce8559e8efa4203329b0a9afeba9d4404c","source":{"kind":"arxiv","id":"2402.04615","version":3},"attestation_state":"computed","paper":{"title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhanshu Sharma, Fedir Zubach, Gilles Baechler, Hassan Mansoor, Jason Lin, Jindong Chen, Maria Wang, Srinivas Sunkara, Victor C\\u{a}rbune, Vincent Etter","submitted_at":"2024-02-07T06:42:33Z","abstract_excerpt":"Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe"},"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":"2402.04615","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T06:42:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2cb658b3a797dc52a8ebbfe8bf578e89d912d240e0df51df57fb3346053dc912","abstract_canon_sha256":"837090dd69f3bbad6c7ecb0bca8cb36ea0f17894fc5b8ce504222df832514db4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:13.161553Z","signature_b64":"6UVenwscT1ZNw6lUgVdnbPxAGexO8dXf2Nkf/jm97HeqIWPlcR+boDJs3JrJuvUMIJi4EQVTP+4H2JSxQqf0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eaa4d2f749955959ec4f2105209a2ce8559e8efa4203329b0a9afeba9d4404c","last_reissued_at":"2026-07-05T08:40:13.160899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:13.160899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhanshu Sharma, Fedir Zubach, Gilles Baechler, Hassan Mansoor, Jason Lin, Jindong Chen, Maria Wang, Srinivas Sunkara, Victor C\\u{a}rbune, Vincent Etter","submitted_at":"2024-02-07T06:42:33Z","abstract_excerpt":"Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04615","kind":"arxiv","version":3},"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/2402.04615/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":"2402.04615","created_at":"2026-07-05T08:40:13.160970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04615v3","created_at":"2026-07-05T08:40:13.160970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04615","created_at":"2026-07-05T08:40:13.160970+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2VE2L3UTFKZ","created_at":"2026-07-05T08:40:13.160970+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2VE2L3UTFKZLHWE","created_at":"2026-07-05T08:40:13.160970+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2VE2L3U","created_at":"2026-07-05T08:40:13.160970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23449","citing_title":"AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10522","citing_title":"GUI-AC: Enhancing Continual Learning in GUI Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23772","citing_title":"PageGuide: Browser extension to assist users in navigating a webpage and locating information","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30059","citing_title":"From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25343","citing_title":"Toward Native Multimodal Modeling: A Roadmap","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17656","citing_title":"MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06477","citing_title":"MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01785","citing_title":"CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10139","citing_title":"Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07972","citing_title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28001","citing_title":"A Pattern Language for Resilient Visual Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23772","citing_title":"PageGuide: Browser extension to assist users in navigating a webpage and locating information","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08516","citing_title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21375","citing_title":"VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2","json":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2.json","graph_json":"https://pith.science/api/pith-number/H2VE2L3UTFKZLHWE6IIFECNCZ2/graph.json","events_json":"https://pith.science/api/pith-number/H2VE2L3UTFKZLHWE6IIFECNCZ2/events.json","paper":"https://pith.science/paper/H2VE2L3U"},"agent_actions":{"view_html":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2","download_json":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2.json","view_paper":"https://pith.science/paper/H2VE2L3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04615&json=true","fetch_graph":"https://pith.science/api/pith-number/H2VE2L3UTFKZLHWE6IIFECNCZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/H2VE2L3UTFKZLHWE6IIFECNCZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2/action/storage_attestation","attest_author":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2/action/author_attestation","sign_citation":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2/action/citation_signature","submit_replication":"https://pith.science/pith/H2VE2L3UTFKZLHWE6IIFECNCZ2/action/replication_record"}},"created_at":"2026-07-05T08:40:13.160970+00:00","updated_at":"2026-07-05T08:40:13.160970+00:00"}