{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:43KOC5XGLVFO53MQODY3PO4Q6M","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":"0875240bf4a2c08e2006afbe0398466cbcdd9f5fc62ab27ab5f6d9cfd1179ea1","cross_cats_sorted":["cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-12T03:13:21Z","title_canon_sha256":"a5533d5e651a8f12987c0640741875c3bfe8f917cda699db8420dbb949fce218"},"schema_version":"1.0","source":{"id":"2507.00008","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00008","created_at":"2026-07-05T12:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00008v2","created_at":"2026-07-05T12:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00008","created_at":"2026-07-05T12:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"43KOC5XGLVFO","created_at":"2026-07-05T12:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"43KOC5XGLVFO53MQ","created_at":"2026-07-05T12:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"43KOC5XG","created_at":"2026-07-05T12:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:5177bf3731bfe1a94e535804d3a6f80e7c90527b8419b8cc673433b6c9c27992","target":"graph","created_at":"2026-07-05T12:05:18Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.00008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grounding natural language queries in graphical user interfaces (GUIs) poses unique challenges due to the diversity of visual elements, spatial clutter, and the ambiguity of language. In this paper, we introduce DiMo-GUI, a training-free framework for GUI grounding that leverages two core strategies: dynamic visual grounding and modality-aware optimization. Instead of treating the GUI as a monolithic image, our method splits the input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models. When predi","authors_text":"Chang Liu, Hang Wu, Hongkai Chen, Ming-Hsuan Yang, Qingwen Ye, Yiwei Wang, Yujun Cai","cross_cats":["cs.CV","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-12T03:13:21Z","title":"DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00008","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f2be5d9ed19d83bc540dc877269e338fe9eb6aced654440ec9cb58ef503d6d0a","target":"record","created_at":"2026-07-05T12:05:18Z","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":"0875240bf4a2c08e2006afbe0398466cbcdd9f5fc62ab27ab5f6d9cfd1179ea1","cross_cats_sorted":["cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-12T03:13:21Z","title_canon_sha256":"a5533d5e651a8f12987c0640741875c3bfe8f917cda699db8420dbb949fce218"},"schema_version":"1.0","source":{"id":"2507.00008","kind":"arxiv","version":2}},"canonical_sha256":"e6d4e176e65d4aeeed9070f1b7bb90f31925a22f8291a2c8993109f523a6833d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6d4e176e65d4aeeed9070f1b7bb90f31925a22f8291a2c8993109f523a6833d","first_computed_at":"2026-07-05T12:05:18.334719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:18.334719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tT+aCyH5h6mg/QIHq8XAv32Ufsv+iMyVA6dmIbRk5/9LYclmg8nlEhDbZMNEbt5QjcwExj7iZZxtYR5io5miBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:18.336176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00008","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2be5d9ed19d83bc540dc877269e338fe9eb6aced654440ec9cb58ef503d6d0a","sha256:5177bf3731bfe1a94e535804d3a6f80e7c90527b8419b8cc673433b6c9c27992"],"state_sha256":"7a831800553a057fa71ce9cf1defba6766e0fea6aeb4e5f1a5ec2253b954e397"}