{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FBWVW44EBEPC4LSRRTAR327TBB","short_pith_number":"pith:FBWVW44E","schema_version":"1.0","canonical_sha256":"286d5b7384091e2e2e518cc11debf30850db08c5dac2e81ff78683266219ea9d","source":{"kind":"arxiv","id":"2301.13280","version":1},"attestation_state":"computed","paper":{"title":"WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jason Wu, Jeffrey Nichols, Jeffrey P. Bigham, Siman Shen, Siyan Wang, Yi-Hao Peng","submitted_at":"2023-01-30T20:47:12Z","abstract_excerpt":"Modeling user interfaces (UIs) from visual information allows systems to make inferences about the functionality and semantics needed to support use cases in accessibility, app automation, and testing. Current datasets for training machine learning models are limited in size due to the costly and time-consuming process of manually collecting and annotating UIs. We crawled the web to construct WebUI, a large dataset of 400,000 rendered web pages associated with automatically extracted metadata. We analyze the composition of WebUI and show that while automatically extracted data is noisy, most e"},"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":"2301.13280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-30T20:47:12Z","cross_cats_sorted":[],"title_canon_sha256":"4f09f5563a88ef332f76ec65705014a6e1dd4d2efef3bfb25e467cfa3ef3bfdf","abstract_canon_sha256":"33b8ed5affa5c40b6d2c5e255e00efe22e9c7883a6b6c5c061a9e5e8a8b292fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:13.202044Z","signature_b64":"dCc00/d7+0kALvhJ2vMOHcbUzBplP6ADsE3ORpiJ6CEG52qL0QlcZ0+E4qy++cN2h6FocPAPxEANO4iF2xbhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"286d5b7384091e2e2e518cc11debf30850db08c5dac2e81ff78683266219ea9d","last_reissued_at":"2026-07-05T05:37:13.201575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:13.201575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jason Wu, Jeffrey Nichols, Jeffrey P. Bigham, Siman Shen, Siyan Wang, Yi-Hao Peng","submitted_at":"2023-01-30T20:47:12Z","abstract_excerpt":"Modeling user interfaces (UIs) from visual information allows systems to make inferences about the functionality and semantics needed to support use cases in accessibility, app automation, and testing. Current datasets for training machine learning models are limited in size due to the costly and time-consuming process of manually collecting and annotating UIs. We crawled the web to construct WebUI, a large dataset of 400,000 rendered web pages associated with automatically extracted metadata. We analyze the composition of WebUI and show that while automatically extracted data is noisy, most e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13280","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/2301.13280/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":"2301.13280","created_at":"2026-07-05T05:37:13.201635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13280v1","created_at":"2026-07-05T05:37:13.201635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13280","created_at":"2026-07-05T05:37:13.201635+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBWVW44EBEPC","created_at":"2026-07-05T05:37:13.201635+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBWVW44EBEPC4LSR","created_at":"2026-07-05T05:37:13.201635+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBWVW44E","created_at":"2026-07-05T05:37:13.201635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09121","citing_title":"MELLON - Multimodal Enhanced LLM for Online Navigation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB","json":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB.json","graph_json":"https://pith.science/api/pith-number/FBWVW44EBEPC4LSRRTAR327TBB/graph.json","events_json":"https://pith.science/api/pith-number/FBWVW44EBEPC4LSRRTAR327TBB/events.json","paper":"https://pith.science/paper/FBWVW44E"},"agent_actions":{"view_html":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB","download_json":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB.json","view_paper":"https://pith.science/paper/FBWVW44E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13280&json=true","fetch_graph":"https://pith.science/api/pith-number/FBWVW44EBEPC4LSRRTAR327TBB/graph.json","fetch_events":"https://pith.science/api/pith-number/FBWVW44EBEPC4LSRRTAR327TBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB/action/storage_attestation","attest_author":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB/action/author_attestation","sign_citation":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB/action/citation_signature","submit_replication":"https://pith.science/pith/FBWVW44EBEPC4LSRRTAR327TBB/action/replication_record"}},"created_at":"2026-07-05T05:37:13.201635+00:00","updated_at":"2026-07-05T05:37:13.201635+00:00"}