{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:62MWV6RBUWA234UGF6USAC4GLQ","short_pith_number":"pith:62MWV6RB","schema_version":"1.0","canonical_sha256":"f6996afa21a581adf2862fa9200b865c203638944917259f1451623c91b88c94","source":{"kind":"arxiv","id":"2608.03270","version":1},"attestation_state":"computed","paper":{"title":"GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guojing Li, Hanyu Yan, Jingtong Gao, Junjia Qi, Shirong Wang, Wanyu Wang, Wenlin Zhang, Xiangyu Zhao, Xian Wu, Xiaopeng Li, Yefeng Zheng, Yimin Deng, Zichuan Fu","submitted_at":"2026-08-04T07:47:37Z","abstract_excerpt":"GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated interfaces because a vision-language model (VLM) may recognize a requested control without locating it precisely enough for interaction. Most existing methods provide various forms of localization assistance, but still rely on a direct click prediction, allowing visual ambiguity or an inaccurate initial estimate to propagate to the final result. In this paper, we introduce GUI-Lens, a coarse-to-fine grounding framework th"},"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":"2608.03270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T07:47:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2381757e2bde261b2f167955a8f1ec991c3d018cb2d9329054e8289ababac2f","abstract_canon_sha256":"7964c1320e442b2a4aed428347217cd1700ac5455b217b26f0558961a66af0f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:36.609251Z","signature_b64":"V57xPEkeb/Tf71hRxdV9axW81KWV+7l00mczMfXPN1Dw4cyrgukuHtLwug/MCySR0MLB2WvyRJxLB1warJz8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6996afa21a581adf2862fa9200b865c203638944917259f1451623c91b88c94","last_reissued_at":"2026-08-05T00:46:36.606927Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:36.606927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guojing Li, Hanyu Yan, Jingtong Gao, Junjia Qi, Shirong Wang, Wanyu Wang, Wenlin Zhang, Xiangyu Zhao, Xian Wu, Xiaopeng Li, Yefeng Zheng, Yimin Deng, Zichuan Fu","submitted_at":"2026-08-04T07:47:37Z","abstract_excerpt":"GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated interfaces because a vision-language model (VLM) may recognize a requested control without locating it precisely enough for interaction. Most existing methods provide various forms of localization assistance, but still rely on a direct click prediction, allowing visual ambiguity or an inaccurate initial estimate to propagate to the final result. In this paper, we introduce GUI-Lens, a coarse-to-fine grounding framework th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03270","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/2608.03270/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":"2608.03270","created_at":"2026-08-05T00:46:36.607719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03270v1","created_at":"2026-08-05T00:46:36.607719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03270","created_at":"2026-08-05T00:46:36.607719+00:00"},{"alias_kind":"pith_short_12","alias_value":"62MWV6RBUWA2","created_at":"2026-08-05T00:46:36.607719+00:00"},{"alias_kind":"pith_short_16","alias_value":"62MWV6RBUWA234UG","created_at":"2026-08-05T00:46:36.607719+00:00"},{"alias_kind":"pith_short_8","alias_value":"62MWV6RB","created_at":"2026-08-05T00:46:36.607719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ","json":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ.json","graph_json":"https://pith.science/api/pith-number/62MWV6RBUWA234UGF6USAC4GLQ/graph.json","events_json":"https://pith.science/api/pith-number/62MWV6RBUWA234UGF6USAC4GLQ/events.json","paper":"https://pith.science/paper/62MWV6RB"},"agent_actions":{"view_html":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ","download_json":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ.json","view_paper":"https://pith.science/paper/62MWV6RB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03270&json=true","fetch_graph":"https://pith.science/api/pith-number/62MWV6RBUWA234UGF6USAC4GLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/62MWV6RBUWA234UGF6USAC4GLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ/action/storage_attestation","attest_author":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ/action/author_attestation","sign_citation":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ/action/citation_signature","submit_replication":"https://pith.science/pith/62MWV6RBUWA234UGF6USAC4GLQ/action/replication_record"}},"created_at":"2026-08-05T00:46:36.607719+00:00","updated_at":"2026-08-05T00:46:36.607719+00:00"}