{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AO6BK5V74MJ4CT5CUTUPHZTKEB","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":"d855ca8afa8f69d148a7dc780e8dbdad764e529552e63863fcb918193d6ace74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-08T12:12:09Z","title_canon_sha256":"e1c36b436ae993ba052abaa403f4afc28f0e3a81eaef99b709c1dfe563392e99"},"schema_version":"1.0","source":{"id":"2604.06995","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.06995","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2604.06995v2","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.06995","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"AO6BK5V74MJ4","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"AO6BK5V74MJ4CT5C","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"AO6BK5V7","created_at":"2026-06-02T01:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:bbacd284574071d46e0f110166cd9fb170a018207b429a24b7d8b170c8c60c7a","target":"graph","created_at":"2026-06-02T01:03:46Z","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":"By enabling Multimodal Large Language Models (MLLMs) to explicitly learn the localization, semantic functions, and practical usage of key UI elements, UILoop achieves precise element discovery and performs interpretable reasoning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That inserting an explicit UI-element learning step into a cyclic Screen-UI-Action process will produce both higher accuracy and better interpretability in MLLMs, without the added structure introducing new failure modes or requiring impractical amounts of supervision."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UI-in-the-Loop makes multimodal models explicitly learn UI element locations, meanings, and uses in a cyclic screen-element-action loop, delivering better UI comprehension and GUI reasoning on a new 26K-sample benchmark."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions."}],"snapshot_sha256":"f61b6607d65f8abf67e5db36beb8920582745aafd00371cdb75d138cdfbbaf70"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.06995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based decision-making, which lacks interpretability and overlooks a comprehensive understanding of UI elements, ultimately leading to task failure. To enhance the understanding and interaction with UIs, we propose an innovative GUI reasoning paradigm called UI-in-the-Loop (UILoop). Our approach treats the GUI reasoning task as a cyclic Screen-UI elements-Action process. By enabling Multimodal Large Language Models (MLLMs) to explicitly le","authors_text":"Biao Yi, Huajun Chen, Songze Li, Tianqi Liu, Wen Zhang, Xiaoke Guo, Zhaoyan Gong, Zhiqiang Liu","cross_cats":[],"headline":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-08T12:12:09Z","title":"What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.06995","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:40:58.055768Z","id":"9d8eb0a4-40fe-44a5-8b4e-6af8b96256a5","model_set":{"reader":"grok-4.3"},"one_line_summary":"UI-in-the-Loop makes multimodal models explicitly learn UI element locations, meanings, and uses in a cyclic screen-element-action loop, delivering better UI comprehension and GUI reasoning on a new 26K-sample benchmark.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions.","strongest_claim":"By enabling Multimodal Large Language Models (MLLMs) to explicitly learn the localization, semantic functions, and practical usage of key UI elements, UILoop achieves precise element discovery and performs interpretable reasoning.","weakest_assumption":"That inserting an explicit UI-element learning step into a cyclic Screen-UI-Action process will produce both higher accuracy and better interpretability in MLLMs, without the added structure introducing new failure modes or requiring impractical amounts of supervision."}},"verdict_id":"9d8eb0a4-40fe-44a5-8b4e-6af8b96256a5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f6a5a1d892ce196ab3213402a2b42cffcfc65fc3ff320682c70e3e6a4c3c391","target":"record","created_at":"2026-06-02T01:03:46Z","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":"d855ca8afa8f69d148a7dc780e8dbdad764e529552e63863fcb918193d6ace74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-08T12:12:09Z","title_canon_sha256":"e1c36b436ae993ba052abaa403f4afc28f0e3a81eaef99b709c1dfe563392e99"},"schema_version":"1.0","source":{"id":"2604.06995","kind":"arxiv","version":2}},"canonical_sha256":"03bc1576bfe313c14fa2a4e8f3e66a207c3ddae444676165c3d5d5068eb6ca29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03bc1576bfe313c14fa2a4e8f3e66a207c3ddae444676165c3d5d5068eb6ca29","first_computed_at":"2026-06-02T01:03:46.790309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:46.790309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLep8s94IOKOMB3GdnIrENPUk/z0WXLqE1RuP/q/DgTiuThCmPnJIH74jKB6ke2+7CZaLxRvR4543TbaKDq3DQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:46.790770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.06995","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f6a5a1d892ce196ab3213402a2b42cffcfc65fc3ff320682c70e3e6a4c3c391","sha256:bbacd284574071d46e0f110166cd9fb170a018207b429a24b7d8b170c8c60c7a"],"state_sha256":"4cf5449de08336ea7f05cc57d624e9bac7c8cb23fc07ea3746061dbb80c691ea"}