{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ST2SGYWZXQ3ZV6AA5RUSPCCJ4","short_pith_number":"pith:6ST2SGYW","schema_version":"1.0","canonical_sha256":"f4a7a91b16cde1bcd7c00763493c424f24482f2c0a9cbe3ce93fa157a03957bf","source":{"kind":"arxiv","id":"2503.06470","version":1},"attestation_state":"computed","paper":{"title":"Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Fei Tang, Guiyang Hou, Hang Zhang, Kaitao Song, Siqi Chen, Weiming Lu, Wenqiao Zhang, Wenqi Zhang, Yongliang Shen, Yueting Zhuang","submitted_at":"2025-03-09T06:14:17Z","abstract_excerpt":"Humans can flexibly switch between different modes of thinking based on task complexity: from rapid intuitive judgments to in-depth analytical understanding. However, current Graphical User Interface (GUI) grounding systems which locate interface elements based on natural language instructions rely solely on immediate prediction without reasoning, struggling to understand complex interface layouts with nested structures and hierarchical relationships, limiting their effectiveness on complex interfaces. Inspired by human dual-system cognition, we present Focus, a novel GUI grounding framework t"},"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":"2503.06470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-09T06:14:17Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"94fd974ad5fc6318a8d6d931ddecbd4c35fbe6ac5815d80f82ede2b242217237","abstract_canon_sha256":"666549985fd601f2c0606887784e67420793dbb51fc749b306374ac5a1915c08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:34.586418Z","signature_b64":"0qk5HEiQNNVE+cCU75EGG1ogkumloiEDqIn0i7e1Y4l2vgMHAmseGevhosPbfAB66gNl+fIqnPihB6N7acuSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4a7a91b16cde1bcd7c00763493c424f24482f2c0a9cbe3ce93fa157a03957bf","last_reissued_at":"2026-07-05T10:27:34.585805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:34.585805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Fei Tang, Guiyang Hou, Hang Zhang, Kaitao Song, Siqi Chen, Weiming Lu, Wenqiao Zhang, Wenqi Zhang, Yongliang Shen, Yueting Zhuang","submitted_at":"2025-03-09T06:14:17Z","abstract_excerpt":"Humans can flexibly switch between different modes of thinking based on task complexity: from rapid intuitive judgments to in-depth analytical understanding. However, current Graphical User Interface (GUI) grounding systems which locate interface elements based on natural language instructions rely solely on immediate prediction without reasoning, struggling to understand complex interface layouts with nested structures and hierarchical relationships, limiting their effectiveness on complex interfaces. Inspired by human dual-system cognition, we present Focus, a novel GUI grounding framework t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06470","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.06470/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":"2503.06470","created_at":"2026-07-05T10:27:34.585887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06470v1","created_at":"2026-07-05T10:27:34.585887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06470","created_at":"2026-07-05T10:27:34.585887+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ST2SGYWZXQ3","created_at":"2026-07-05T10:27:34.585887+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ST2SGYWZXQ3ZV6A","created_at":"2026-07-05T10:27:34.585887+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ST2SGYW","created_at":"2026-07-05T10:27:34.585887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03236","citing_title":"Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":243,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4","json":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4.json","graph_json":"https://pith.science/api/pith-number/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/graph.json","events_json":"https://pith.science/api/pith-number/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/events.json","paper":"https://pith.science/paper/6ST2SGYW"},"agent_actions":{"view_html":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4","download_json":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4.json","view_paper":"https://pith.science/paper/6ST2SGYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06470&json=true","fetch_graph":"https://pith.science/api/pith-number/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/action/storage_attestation","attest_author":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/action/author_attestation","sign_citation":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/action/citation_signature","submit_replication":"https://pith.science/pith/6ST2SGYWZXQ3ZV6AA5RUSPCCJ4/action/replication_record"}},"created_at":"2026-07-05T10:27:34.585887+00:00","updated_at":"2026-07-05T10:27:34.585887+00:00"}