{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","short_pith_number":"pith:FJ5ZTZMR","schema_version":"1.0","canonical_sha256":"2a7b99e591d8ceb04f597ff07bb5291a8861d27706eb51220b14861b30569845","source":{"kind":"arxiv","id":"2604.13019","version":2},"attestation_state":"computed","paper":{"title":"PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Multi-turn refinement using visual feedback from prior attempts achieves higher click precision and task success in GUI grounding for dense coding interfaces than single-shot prediction.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaurav Mittal, Himangi Mittal, Nelson Daniel Troncoso, Yu Hu","submitted_at":"2026-04-14T17:55:46Z","abstract_excerpt":"Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen actions, but editing-level grounding in dense coding interfaces (such as VS Code and Cursor), where sub-pixel accuracy is required to interact with dense IDE elements, remains underexplored. Existing approaches typically rely on single-shot coordinate prediction, which lacks a mechanism for error correction and often fails in high-density interfaces. In this technical report, we conduct an empirical study of pixel-precise cursor localization in cod"},"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":"2604.13019","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-14T17:55:46Z","cross_cats_sorted":[],"title_canon_sha256":"3ba4c5b35d5bfde92255de5c9bc1bef1817982c9ddd07e88ccd6610ed2bc22e1","abstract_canon_sha256":"5b7716a3ed8ebd7584dc7f8186a66e0ce968e2aac856dc95ba0ea4a140aac235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:40.029391Z","signature_b64":"QmdY6wJDL/w2HxV93mEpChNy5oZgxm4TZeuRcrPa/wUPMyVYDeSQoK7BH9TdDBF45YulPas1mMoCIeUmPkAVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a7b99e591d8ceb04f597ff07bb5291a8861d27706eb51220b14861b30569845","last_reissued_at":"2026-05-28T01:04:40.028897Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:40.028897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Multi-turn refinement using visual feedback from prior attempts achieves higher click precision and task success in GUI grounding for dense coding interfaces than single-shot prediction.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaurav Mittal, Himangi Mittal, Nelson Daniel Troncoso, Yu Hu","submitted_at":"2026-04-14T17:55:46Z","abstract_excerpt":"Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen actions, but editing-level grounding in dense coding interfaces (such as VS Code and Cursor), where sub-pixel accuracy is required to interact with dense IDE elements, remains underexplored. Existing approaches typically rely on single-shot coordinate prediction, which lacks a mechanism for error correction and often fails in high-density interfaces. In this technical report, we conduct an empirical study of pixel-precise cursor localization in cod"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"multi-turn refinement significantly outperforms state-of-the-art single-shot models in both click precision and overall task success rate.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That models can reliably interpret and act on visual feedback from prior attempts to self-correct without introducing additional errors or failing to adapt to dynamic UI changes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Multi-turn visual feedback refinement outperforms single-shot coordinate prediction for pixel-precise GUI grounding in complex coding environments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-turn refinement using visual feedback from prior attempts achieves higher click precision and task success in GUI grounding for dense coding interfaces than single-shot prediction.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"12c4fcb6b2409764b3791491afea96a9bae99429f01d47a96fa568aacd7e933e"},"source":{"id":"2604.13019","kind":"arxiv","version":2},"verdict":{"id":"8cbffd65-8462-413f-965f-0b5aa4c6d479","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:54:16.329493Z","strongest_claim":"multi-turn refinement significantly outperforms state-of-the-art single-shot models in both click precision and overall task success rate.","one_line_summary":"Multi-turn visual feedback refinement outperforms single-shot coordinate prediction for pixel-precise GUI grounding in complex coding environments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That models can reliably interpret and act on visual feedback from prior attempts to self-correct without introducing additional errors or failing to adapt to dynamic UI changes.","pith_extraction_headline":"Multi-turn refinement using visual feedback from prior attempts achieves higher click precision and task success in GUI grounding for dense coding interfaces than single-shot prediction."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.13019/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":"2604.13019","created_at":"2026-05-28T01:04:40.028960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.13019v2","created_at":"2026-05-28T01:04:40.028960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13019","created_at":"2026-05-28T01:04:40.028960+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJ5ZTZMR3DHL","created_at":"2026-05-28T01:04:40.028960+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJ5ZTZMR3DHLAT2Z","created_at":"2026-05-28T01:04:40.028960+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJ5ZTZMR","created_at":"2026-05-28T01:04:40.028960+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/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","json":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK.json","graph_json":"https://pith.science/api/pith-number/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/graph.json","events_json":"https://pith.science/api/pith-number/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/events.json","paper":"https://pith.science/paper/FJ5ZTZMR"},"agent_actions":{"view_html":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","download_json":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK.json","view_paper":"https://pith.science/paper/FJ5ZTZMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.13019&json=true","fetch_graph":"https://pith.science/api/pith-number/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/graph.json","fetch_events":"https://pith.science/api/pith-number/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/action/storage_attestation","attest_author":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/action/author_attestation","sign_citation":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/action/citation_signature","submit_replication":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/action/replication_record"}},"created_at":"2026-05-28T01:04:40.028960+00:00","updated_at":"2026-05-28T01:04:40.028960+00:00"}