{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZHGT3MR676544CF3CCN4447YLF","short_pith_number":"pith:ZHGT3MR6","schema_version":"1.0","canonical_sha256":"c9cd3db23effbbce08bb109bce73f8596f65eaeac04bf7e7fdd54a9e24febceb","source":{"kind":"arxiv","id":"2504.11257","version":4},"attestation_state":"computed","paper":{"title":"UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.HC","authors_text":"Xiaoyi Zhang, Xinyi Liu, Yan Lu, Ziyun Zhang","submitted_at":"2025-04-15T14:56:21Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models are accelerating the development of Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities to enhance productivity on digital devices. Compared to approaches predicated on GUI metadata, which are platform-dependent and vulnerable to implementation variations, vision-based approaches offer broader applicability. In this vision-based paradigm, the GUI instruction grounding, which maps user instruction to the location of corresponding element on the given screenshot, remains a critical challenge, particularl"},"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":"2504.11257","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:56:21Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"78c2a8a94d1e9cbb7988097feb13ec398f3d953b18d9f57eccc1fd0083465829","abstract_canon_sha256":"2d43d02aee18f667c20640ecf7b72c80cd191d806db0cf2b3b65b30ac46f0398"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:33.725744Z","signature_b64":"esYdtCTB9/SMBEkfc6rwbSEobFRy71QAJvxUVHRwpj4Q/wPoSciEJKV1LYr2QDTM1bVzIE09d/cTEmqMIyrlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9cd3db23effbbce08bb109bce73f8596f65eaeac04bf7e7fdd54a9e24febceb","last_reissued_at":"2026-07-05T11:45:33.725206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:33.725206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.HC","authors_text":"Xiaoyi Zhang, Xinyi Liu, Yan Lu, Ziyun Zhang","submitted_at":"2025-04-15T14:56:21Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models are accelerating the development of Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities to enhance productivity on digital devices. Compared to approaches predicated on GUI metadata, which are platform-dependent and vulnerable to implementation variations, vision-based approaches offer broader applicability. In this vision-based paradigm, the GUI instruction grounding, which maps user instruction to the location of corresponding element on the given screenshot, remains a critical challenge, particularl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11257","kind":"arxiv","version":4},"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/2504.11257/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":"2504.11257","created_at":"2026-07-05T11:45:33.725267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11257v4","created_at":"2026-07-05T11:45:33.725267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11257","created_at":"2026-07-05T11:45:33.725267+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHGT3MR67654","created_at":"2026-07-05T11:45:33.725267+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHGT3MR676544CF3","created_at":"2026-07-05T11:45:33.725267+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHGT3MR6","created_at":"2026-07-05T11:45:33.725267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21268","citing_title":"Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF","json":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF.json","graph_json":"https://pith.science/api/pith-number/ZHGT3MR676544CF3CCN4447YLF/graph.json","events_json":"https://pith.science/api/pith-number/ZHGT3MR676544CF3CCN4447YLF/events.json","paper":"https://pith.science/paper/ZHGT3MR6"},"agent_actions":{"view_html":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF","download_json":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF.json","view_paper":"https://pith.science/paper/ZHGT3MR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11257&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHGT3MR676544CF3CCN4447YLF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHGT3MR676544CF3CCN4447YLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF/action/storage_attestation","attest_author":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF/action/author_attestation","sign_citation":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF/action/citation_signature","submit_replication":"https://pith.science/pith/ZHGT3MR676544CF3CCN4447YLF/action/replication_record"}},"created_at":"2026-07-05T11:45:33.725267+00:00","updated_at":"2026-07-05T11:45:33.725267+00:00"}