{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NHMZDD4GHM2IO5O23I2GF336XE","short_pith_number":"pith:NHMZDD4G","schema_version":"1.0","canonical_sha256":"69d9918f863b348775dada3462ef7eb93de99a9f5207ab2b7a33e15c36a6a6ba","source":{"kind":"arxiv","id":"2010.04295","version":1},"attestation_state":"computed","paper":{"title":"Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.LG","authors_text":"Gang Li, Hong Li, Jingjie Zheng, Luheng He, Yang Li, Zhiwei Guan","submitted_at":"2020-10-08T22:56:03Z","abstract_excerpt":"Natural language descriptions of user interface (UI) elements such as alternative text are crucial for accessibility and language-based interaction in general. Yet, these descriptions are constantly missing in mobile UIs. We propose widget captioning, a novel task for automatically generating language descriptions for UI elements from multimodal input including both the image and the structural representations of user interfaces. We collected a large-scale dataset for widget captioning with crowdsourcing. Our dataset contains 162,859 language phrases created by human workers for annotating 61,"},"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":"2010.04295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T22:56:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"96a77ac61dc4531b5be32daebee7bdf91db239c3fe9f45392c2ac3470096fd0c","abstract_canon_sha256":"629fb921369830507f6864b879130c230a80ab373967f9fd9466d3293d881e8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:35.432030Z","signature_b64":"khkY6/EtQXnsN8nZcdf57X5xcVG7gn7jjr50CVstcLP2yOV7QkQIfgpRDLlkJk3qFKHQ9ed+fNnTN/3J6jAcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d9918f863b348775dada3462ef7eb93de99a9f5207ab2b7a33e15c36a6a6ba","last_reissued_at":"2026-07-05T01:41:35.431608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:35.431608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.LG","authors_text":"Gang Li, Hong Li, Jingjie Zheng, Luheng He, Yang Li, Zhiwei Guan","submitted_at":"2020-10-08T22:56:03Z","abstract_excerpt":"Natural language descriptions of user interface (UI) elements such as alternative text are crucial for accessibility and language-based interaction in general. Yet, these descriptions are constantly missing in mobile UIs. We propose widget captioning, a novel task for automatically generating language descriptions for UI elements from multimodal input including both the image and the structural representations of user interfaces. We collected a large-scale dataset for widget captioning with crowdsourcing. Our dataset contains 162,859 language phrases created by human workers for annotating 61,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04295","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/2010.04295/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":"2010.04295","created_at":"2026-07-05T01:41:35.431664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04295v1","created_at":"2026-07-05T01:41:35.431664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04295","created_at":"2026-07-05T01:41:35.431664+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHMZDD4GHM2I","created_at":"2026-07-05T01:41:35.431664+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHMZDD4GHM2IO5O2","created_at":"2026-07-05T01:41:35.431664+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHMZDD4G","created_at":"2026-07-05T01:41:35.431664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17656","citing_title":"MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":252,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14239","citing_title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02345","citing_title":"UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05525","citing_title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21268","citing_title":"Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":136,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE","json":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE.json","graph_json":"https://pith.science/api/pith-number/NHMZDD4GHM2IO5O23I2GF336XE/graph.json","events_json":"https://pith.science/api/pith-number/NHMZDD4GHM2IO5O23I2GF336XE/events.json","paper":"https://pith.science/paper/NHMZDD4G"},"agent_actions":{"view_html":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE","download_json":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE.json","view_paper":"https://pith.science/paper/NHMZDD4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04295&json=true","fetch_graph":"https://pith.science/api/pith-number/NHMZDD4GHM2IO5O23I2GF336XE/graph.json","fetch_events":"https://pith.science/api/pith-number/NHMZDD4GHM2IO5O23I2GF336XE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE/action/storage_attestation","attest_author":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE/action/author_attestation","sign_citation":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE/action/citation_signature","submit_replication":"https://pith.science/pith/NHMZDD4GHM2IO5O23I2GF336XE/action/replication_record"}},"created_at":"2026-07-05T01:41:35.431664+00:00","updated_at":"2026-07-05T01:41:35.431664+00:00"}