{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:266KTUGCVPUAPOQNKJXXDEB3LO","short_pith_number":"pith:266KTUGC","schema_version":"1.0","canonical_sha256":"d7bca9d0c2abe807ba0d526f71903b5bae6813593f699e56b4fc203d423c33b5","source":{"kind":"arxiv","id":"2502.01977","version":2},"attestation_state":"computed","paper":{"title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxin Li, Jingfan Chen, Jingran Su, Qing Li, Yuntao Chen, Zhaoxiang Zhang","submitted_at":"2025-02-04T03:39:59Z","abstract_excerpt":"User interface understanding with vision-language models (VLMs) has received much attention due to its potential for enhancing software automation. However, existing datasets used to build UI-VLMs either only contain large-scale context-free element annotations or contextualized functional descriptions for elements at a small scale. In this work, we propose the \\textbf{AutoGUI} pipeline for automatically annotating UI elements with detailed functionality descriptions at scale. Specifically, we leverage large language models (LLMs) to infer element functionality by comparing UI state changes be"},"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":"2502.01977","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T03:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"451f3803f050357872a17422b1d1a659369510f9df94c3d2418c3c2cf835e129","abstract_canon_sha256":"a5d4a2b37e0b727d36b8f4cd86f04496e4439b20f38821a9550717d69601e834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:40.832163Z","signature_b64":"pKl4VSdheC4y1DS2gu3Wkdaha2hjV8rvdijMJKQWmnLWN/Mxd8nBO8hSOKPTfE25Q2i4lWe47N0FeeHjA76ZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7bca9d0c2abe807ba0d526f71903b5bae6813593f699e56b4fc203d423c33b5","last_reissued_at":"2026-07-05T11:17:40.831487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:40.831487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxin Li, Jingfan Chen, Jingran Su, Qing Li, Yuntao Chen, Zhaoxiang Zhang","submitted_at":"2025-02-04T03:39:59Z","abstract_excerpt":"User interface understanding with vision-language models (VLMs) has received much attention due to its potential for enhancing software automation. However, existing datasets used to build UI-VLMs either only contain large-scale context-free element annotations or contextualized functional descriptions for elements at a small scale. In this work, we propose the \\textbf{AutoGUI} pipeline for automatically annotating UI elements with detailed functionality descriptions at scale. Specifically, we leverage large language models (LLMs) to infer element functionality by comparing UI state changes be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01977","kind":"arxiv","version":2},"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/2502.01977/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":"2502.01977","created_at":"2026-07-05T11:17:40.831566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01977v2","created_at":"2026-07-05T11:17:40.831566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01977","created_at":"2026-07-05T11:17:40.831566+00:00"},{"alias_kind":"pith_short_12","alias_value":"266KTUGCVPUA","created_at":"2026-07-05T11:17:40.831566+00:00"},{"alias_kind":"pith_short_16","alias_value":"266KTUGCVPUAPOQN","created_at":"2026-07-05T11:17:40.831566+00:00"},{"alias_kind":"pith_short_8","alias_value":"266KTUGC","created_at":"2026-07-05T11:17:40.831566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00390","citing_title":"Zamba2-VL Technical Report","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21858","citing_title":"ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08560","citing_title":"ZAYA1-VL-8B Technical Report","ref_index":157,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO","json":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO.json","graph_json":"https://pith.science/api/pith-number/266KTUGCVPUAPOQNKJXXDEB3LO/graph.json","events_json":"https://pith.science/api/pith-number/266KTUGCVPUAPOQNKJXXDEB3LO/events.json","paper":"https://pith.science/paper/266KTUGC"},"agent_actions":{"view_html":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO","download_json":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO.json","view_paper":"https://pith.science/paper/266KTUGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01977&json=true","fetch_graph":"https://pith.science/api/pith-number/266KTUGCVPUAPOQNKJXXDEB3LO/graph.json","fetch_events":"https://pith.science/api/pith-number/266KTUGCVPUAPOQNKJXXDEB3LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO/action/storage_attestation","attest_author":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO/action/author_attestation","sign_citation":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO/action/citation_signature","submit_replication":"https://pith.science/pith/266KTUGCVPUAPOQNKJXXDEB3LO/action/replication_record"}},"created_at":"2026-07-05T11:17:40.831566+00:00","updated_at":"2026-07-05T11:17:40.831566+00:00"}