{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","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":"5b7716a3ed8ebd7584dc7f8186a66e0ce968e2aac856dc95ba0ea4a140aac235","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-14T17:55:46Z","title_canon_sha256":"3ba4c5b35d5bfde92255de5c9bc1bef1817982c9ddd07e88ccd6610ed2bc22e1"},"schema_version":"1.0","source":{"id":"2604.13019","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.13019","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2604.13019v2","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13019","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"FJ5ZTZMR3DHL","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"FJ5ZTZMR3DHLAT2Z","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"FJ5ZTZMR","created_at":"2026-05-28T01:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:4316d96df2180caa7a27a5c63e17c667d2e469b0ab92528e857be476629540fb","target":"graph","created_at":"2026-05-28T01:04:40Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"multi-turn refinement significantly outperforms state-of-the-art single-shot models in both click precision and overall task success rate."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Multi-turn visual feedback refinement outperforms single-shot coordinate prediction for pixel-precise GUI grounding in complex coding environments."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"12c4fcb6b2409764b3791491afea96a9bae99429f01d47a96fa568aacd7e933e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.13019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gaurav Mittal, Himangi Mittal, Nelson Daniel Troncoso, Yu Hu","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-14T17:55:46Z","title":"PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.13019","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:54:16.329493Z","id":"8cbffd65-8462-413f-965f-0b5aa4c6d479","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"multi-turn refinement significantly outperforms state-of-the-art single-shot models in both click precision and overall task success rate.","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."}},"verdict_id":"8cbffd65-8462-413f-965f-0b5aa4c6d479"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ccb6b23f1203d5d55d032dc8600a55a9c8caa3b9b3d53e392c0e8b65c1c1504b","target":"record","created_at":"2026-05-28T01:04:40Z","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":"5b7716a3ed8ebd7584dc7f8186a66e0ce968e2aac856dc95ba0ea4a140aac235","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-14T17:55:46Z","title_canon_sha256":"3ba4c5b35d5bfde92255de5c9bc1bef1817982c9ddd07e88ccd6610ed2bc22e1"},"schema_version":"1.0","source":{"id":"2604.13019","kind":"arxiv","version":2}},"canonical_sha256":"2a7b99e591d8ceb04f597ff07bb5291a8861d27706eb51220b14861b30569845","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a7b99e591d8ceb04f597ff07bb5291a8861d27706eb51220b14861b30569845","first_computed_at":"2026-05-28T01:04:40.028897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:40.028897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QmdY6wJDL/w2HxV93mEpChNy5oZgxm4TZeuRcrPa/wUPMyVYDeSQoK7BH9TdDBF45YulPas1mMoCIeUmPkAVDA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:40.029391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.13019","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccb6b23f1203d5d55d032dc8600a55a9c8caa3b9b3d53e392c0e8b65c1c1504b","sha256:4316d96df2180caa7a27a5c63e17c667d2e469b0ab92528e857be476629540fb"],"state_sha256":"29b6b6f75927be72d88aeeac2264697a58d2b5c26e191bafef65653a16203913"}