{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GSKR7OZDNQ373527RBJIWWOKAV","short_pith_number":"pith:GSKR7OZD","schema_version":"1.0","canonical_sha256":"34951fbb236c37fdf75f88528b59ca0562314ad5285df56096fc12b8c501544f","source":{"kind":"arxiv","id":"2411.13591","version":7},"attestation_state":"computed","paper":{"title":"Improved GUI Grounding via Iterative Narrowing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anthony Nguyen","submitted_at":"2024-11-18T05:47:12Z","abstract_excerpt":"Graphical User Interface (GUI) grounding plays a crucial role in enhancing the capabilities of Vision-Language Model (VLM) agents. While general VLMs, such as GPT-4V, demonstrate strong performance across various tasks, their proficiency in GUI grounding remains suboptimal. Recent studies have focused on fine-tuning these models specifically for zero-shot GUI grounding, yielding significant improvements over baseline performance. We introduce a visual prompting framework that employs an iterative narrowing mechanism to further improve the performance of both general and fine-tuned models in GU"},"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":"2411.13591","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T05:47:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e0149ca82b1b97bf5204ca3baa5ed30bea6aff8a7e566a31707986f058edc190","abstract_canon_sha256":"eb4f2014461eb6f249ab48613d3a91ef8d01577811606cd5d0d20dc49f60786b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:11.594899Z","signature_b64":"IZFZ/LjBcpiJoA+ZtnIUZ4VPL1BbxOHp3Whiiacmh+pmgD+K/WSaMQEgxIOozFpVcmB+V2qoUIollndGaEBABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34951fbb236c37fdf75f88528b59ca0562314ad5285df56096fc12b8c501544f","last_reissued_at":"2026-07-05T12:09:11.594409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:11.594409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved GUI Grounding via Iterative Narrowing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anthony Nguyen","submitted_at":"2024-11-18T05:47:12Z","abstract_excerpt":"Graphical User Interface (GUI) grounding plays a crucial role in enhancing the capabilities of Vision-Language Model (VLM) agents. While general VLMs, such as GPT-4V, demonstrate strong performance across various tasks, their proficiency in GUI grounding remains suboptimal. Recent studies have focused on fine-tuning these models specifically for zero-shot GUI grounding, yielding significant improvements over baseline performance. We introduce a visual prompting framework that employs an iterative narrowing mechanism to further improve the performance of both general and fine-tuned models in GU"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13591","kind":"arxiv","version":7},"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/2411.13591/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":"2411.13591","created_at":"2026-07-05T12:09:11.594472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13591v7","created_at":"2026-07-05T12:09:11.594472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13591","created_at":"2026-07-05T12:09:11.594472+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSKR7OZDNQ37","created_at":"2026-07-05T12:09:11.594472+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSKR7OZDNQ373527","created_at":"2026-07-05T12:09:11.594472+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSKR7OZD","created_at":"2026-07-05T12:09:11.594472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04046","citing_title":"Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30084","citing_title":"One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":213,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12549","citing_title":"What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs","ref_index":40,"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":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14113","citing_title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV","json":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV.json","graph_json":"https://pith.science/api/pith-number/GSKR7OZDNQ373527RBJIWWOKAV/graph.json","events_json":"https://pith.science/api/pith-number/GSKR7OZDNQ373527RBJIWWOKAV/events.json","paper":"https://pith.science/paper/GSKR7OZD"},"agent_actions":{"view_html":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV","download_json":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV.json","view_paper":"https://pith.science/paper/GSKR7OZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13591&json=true","fetch_graph":"https://pith.science/api/pith-number/GSKR7OZDNQ373527RBJIWWOKAV/graph.json","fetch_events":"https://pith.science/api/pith-number/GSKR7OZDNQ373527RBJIWWOKAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV/action/storage_attestation","attest_author":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV/action/author_attestation","sign_citation":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV/action/citation_signature","submit_replication":"https://pith.science/pith/GSKR7OZDNQ373527RBJIWWOKAV/action/replication_record"}},"created_at":"2026-07-05T12:09:11.594472+00:00","updated_at":"2026-07-05T12:09:11.594472+00:00"}