{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","short_pith_number":"pith:FJ5ZTZMR","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"},"canonical_sha256":"2a7b99e591d8ceb04f597ff07bb5291a8861d27706eb51220b14861b30569845","source":{"kind":"arxiv","id":"2604.13019","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","target":"record","payload":{"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"},"canonical_sha256":"2a7b99e591d8ceb04f597ff07bb5291a8861d27706eb51220b14861b30569845","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"},"source_kind":"arxiv","source_id":"2604.13019","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMUa1JCGxcMTa8JMH3Od7/kCC9XXJCYYq8fH3KAUNZI7MaYvSDFnqEUNwZD8cHLvpd/tpfcXPBZl9xIP4TqhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:31:34.652506Z"},"content_sha256":"ccb6b23f1203d5d55d032dc8600a55a9c8caa3b9b3d53e392c0e8b65c1c1504b","schema_version":"1.0","event_id":"sha256:ccb6b23f1203d5d55d032dc8600a55a9c8caa3b9b3d53e392c0e8b65c1c1504b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","target":"graph","payload":{"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"},"verdict_id":"8cbffd65-8462-413f-965f-0b5aa4c6d479"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tvsRJMOt5S4itiV5vSkvxmEbiWAVTtYVFswcRrzNscR/SVLSlAQvoFaCkRcaL5cFw3Lg5lgK6myJGBwmVzCUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:31:34.653121Z"},"content_sha256":"4316d96df2180caa7a27a5c63e17c667d2e469b0ab92528e857be476629540fb","schema_version":"1.0","event_id":"sha256:4316d96df2180caa7a27a5c63e17c667d2e469b0ab92528e857be476629540fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/bundle.json","state_url":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T22:31:34Z","links":{"resolver":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK","bundle":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/bundle.json","state":"https://pith.science/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJ5ZTZMR3DHLAT2ZP7YHXNJJDK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vl/K67mfzWvVar2H+6Q4+dTYrTbgXmidt0z7h8ZddH9ecz8yM2ZcaEZZY7wtPzgoh2c6RrrRc33n7ntVD7IZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T22:31:34.656258Z","bundle_sha256":"2ab740005dece3324de7673bad67559640d96af9bf76f3d2cf139721bd03d760"}}