{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:62MWV6RBUWA234UGF6USAC4GLQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7964c1320e442b2a4aed428347217cd1700ac5455b217b26f0558961a66af0f1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T07:47:37Z","title_canon_sha256":"d2381757e2bde261b2f167955a8f1ec991c3d018cb2d9329054e8289ababac2f"},"schema_version":"1.0","source":{"id":"2608.03270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03270","created_at":"2026-08-05T00:46:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03270v1","created_at":"2026-08-05T00:46:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03270","created_at":"2026-08-05T00:46:36Z"},{"alias_kind":"pith_short_12","alias_value":"62MWV6RBUWA2","created_at":"2026-08-05T00:46:36Z"},{"alias_kind":"pith_short_16","alias_value":"62MWV6RBUWA234UG","created_at":"2026-08-05T00:46:36Z"},{"alias_kind":"pith_short_8","alias_value":"62MWV6RB","created_at":"2026-08-05T00:46:36Z"}],"graph_snapshots":[{"event_id":"sha256:3ad630225e18cbc4b51afad69e12ca804713cc38ea0f86e2a8156857694db227","target":"graph","created_at":"2026-08-05T00:46:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.03270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T07:47:37Z","title":"GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03270","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:81948fa2cf9dbf1b2649a9a9bd043d278f401c4a94cc099efb375be05c7b14d7","target":"record","created_at":"2026-08-05T00:46:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7964c1320e442b2a4aed428347217cd1700ac5455b217b26f0558961a66af0f1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T07:47:37Z","title_canon_sha256":"d2381757e2bde261b2f167955a8f1ec991c3d018cb2d9329054e8289ababac2f"},"schema_version":"1.0","source":{"id":"2608.03270","kind":"arxiv","version":1}},"canonical_sha256":"f6996afa21a581adf2862fa9200b865c203638944917259f1451623c91b88c94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6996afa21a581adf2862fa9200b865c203638944917259f1451623c91b88c94","first_computed_at":"2026-08-05T00:46:36.606927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:46:36.606927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V57xPEkeb/Tf71hRxdV9axW81KWV+7l00mczMfXPN1Dw4cyrgukuHtLwug/MCySR0MLB2WvyRJxLB1warJz8AA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:46:36.609251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81948fa2cf9dbf1b2649a9a9bd043d278f401c4a94cc099efb375be05c7b14d7","sha256:3ad630225e18cbc4b51afad69e12ca804713cc38ea0f86e2a8156857694db227"],"state_sha256":"54ef5554ebc532bd5bdbb5010bfde6b17ac77edd0dbeb1439bd8704a5135c52e"}