{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZHGT3MR676544CF3CCN4447YLF","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":"2d43d02aee18f667c20640ecf7b72c80cd191d806db0cf2b3b65b30ac46f0398","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:56:21Z","title_canon_sha256":"78c2a8a94d1e9cbb7988097feb13ec398f3d953b18d9f57eccc1fd0083465829"},"schema_version":"1.0","source":{"id":"2504.11257","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11257","created_at":"2026-07-05T11:45:33Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11257v4","created_at":"2026-07-05T11:45:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11257","created_at":"2026-07-05T11:45:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZHGT3MR67654","created_at":"2026-07-05T11:45:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZHGT3MR676544CF3","created_at":"2026-07-05T11:45:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZHGT3MR6","created_at":"2026-07-05T11:45:33Z"}],"graph_snapshots":[{"event_id":"sha256:388c29dbec197c13e9dce72473db10980159b5cfad409332f794be30dbafa28c","target":"graph","created_at":"2026-07-05T11:45:33Z","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/2504.11257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Xiaoyi Zhang, Xinyi Liu, Yan Lu, Ziyun Zhang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:56:21Z","title":"UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11257","kind":"arxiv","version":4},"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":"sha256:2bffea8e629a0537de0fb608138881361dc6d77142f105052dc7015b034fc00b","target":"record","created_at":"2026-07-05T11:45:33Z","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":"2d43d02aee18f667c20640ecf7b72c80cd191d806db0cf2b3b65b30ac46f0398","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T14:56:21Z","title_canon_sha256":"78c2a8a94d1e9cbb7988097feb13ec398f3d953b18d9f57eccc1fd0083465829"},"schema_version":"1.0","source":{"id":"2504.11257","kind":"arxiv","version":4}},"canonical_sha256":"c9cd3db23effbbce08bb109bce73f8596f65eaeac04bf7e7fdd54a9e24febceb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9cd3db23effbbce08bb109bce73f8596f65eaeac04bf7e7fdd54a9e24febceb","first_computed_at":"2026-07-05T11:45:33.725206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:33.725206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"esYdtCTB9/SMBEkfc6rwbSEobFRy71QAJvxUVHRwpj4Q/wPoSciEJKV1LYr2QDTM1bVzIE09d/cTEmqMIyrlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:33.725744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11257","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bffea8e629a0537de0fb608138881361dc6d77142f105052dc7015b034fc00b","sha256:388c29dbec197c13e9dce72473db10980159b5cfad409332f794be30dbafa28c"],"state_sha256":"e73189f21a438795dd8bc906f289914701c90d5787a3bb3fd3eee582a8d42d3e"}