{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CASGOQGFFYFL54STLYIHN5H7FV","short_pith_number":"pith:CASGOQGF","schema_version":"1.0","canonical_sha256":"10246740c52e0abef2535e1076f4ff2d49c02eb6327ebcac1ac7e7a2ecdd1f38","source":{"kind":"arxiv","id":"2412.09362","version":1},"attestation_state":"computed","paper":{"title":"Falcon-UI: Understanding GUI Before Following User Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Ma, Chang Liu, Gengluo Li, Huawen Shen, Xiangyang Ji, Xinlong Wang, Yu Zhou","submitted_at":"2024-12-12T15:29:36Z","abstract_excerpt":"Pursuing human-like interaction for Graphical User Interface (GUI) agents requires understanding the GUI context and following user instructions. However, existing works typically couple these two aspects and focus more on instruct-following abilities, while ignoring the importance of understanding the GUI context. In this paper, we introduce an instruction-free GUI navigation dataset, termed Insight-UI Dataset, to enhance model comprehension of GUI environments. Insight-UI Dataset is automatically generated from the Common Crawl corpus, simulating various platforms -- including iOS, Android, "},"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":"2412.09362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T15:29:36Z","cross_cats_sorted":[],"title_canon_sha256":"8a1135560348d630e1dd600421e68def761c1b62a6490e1605aa45f32fe287eb","abstract_canon_sha256":"f59948513cd52af0ea3505ebba61b3a79ab106f9982d1685d377c15ad41c16f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:23.650513Z","signature_b64":"2w5mFiP6Xljf/34k49KsUub0jsQpvrvAlQQvAXh73fB+PVbxUntagOXrgPBXtl72lk7oAMX17zLEP97O8djSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10246740c52e0abef2535e1076f4ff2d49c02eb6327ebcac1ac7e7a2ecdd1f38","last_reissued_at":"2026-07-05T09:48:23.650119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:23.650119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Falcon-UI: Understanding GUI Before Following User Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Ma, Chang Liu, Gengluo Li, Huawen Shen, Xiangyang Ji, Xinlong Wang, Yu Zhou","submitted_at":"2024-12-12T15:29:36Z","abstract_excerpt":"Pursuing human-like interaction for Graphical User Interface (GUI) agents requires understanding the GUI context and following user instructions. However, existing works typically couple these two aspects and focus more on instruct-following abilities, while ignoring the importance of understanding the GUI context. In this paper, we introduce an instruction-free GUI navigation dataset, termed Insight-UI Dataset, to enhance model comprehension of GUI environments. Insight-UI Dataset is automatically generated from the Common Crawl corpus, simulating various platforms -- including iOS, Android, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09362","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/2412.09362/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":"2412.09362","created_at":"2026-07-05T09:48:23.650168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09362v1","created_at":"2026-07-05T09:48:23.650168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09362","created_at":"2026-07-05T09:48:23.650168+00:00"},{"alias_kind":"pith_short_12","alias_value":"CASGOQGFFYFL","created_at":"2026-07-05T09:48:23.650168+00:00"},{"alias_kind":"pith_short_16","alias_value":"CASGOQGFFYFL54ST","created_at":"2026-07-05T09:48:23.650168+00:00"},{"alias_kind":"pith_short_8","alias_value":"CASGOQGF","created_at":"2026-07-05T09:48:23.650168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15542","citing_title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV","json":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV.json","graph_json":"https://pith.science/api/pith-number/CASGOQGFFYFL54STLYIHN5H7FV/graph.json","events_json":"https://pith.science/api/pith-number/CASGOQGFFYFL54STLYIHN5H7FV/events.json","paper":"https://pith.science/paper/CASGOQGF"},"agent_actions":{"view_html":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV","download_json":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV.json","view_paper":"https://pith.science/paper/CASGOQGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09362&json=true","fetch_graph":"https://pith.science/api/pith-number/CASGOQGFFYFL54STLYIHN5H7FV/graph.json","fetch_events":"https://pith.science/api/pith-number/CASGOQGFFYFL54STLYIHN5H7FV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV/action/storage_attestation","attest_author":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV/action/author_attestation","sign_citation":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV/action/citation_signature","submit_replication":"https://pith.science/pith/CASGOQGFFYFL54STLYIHN5H7FV/action/replication_record"}},"created_at":"2026-07-05T09:48:23.650168+00:00","updated_at":"2026-07-05T09:48:23.650168+00:00"}