{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R6CLSEYLKRE42CS5DSUOSDLKML","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":"bc2bae133e7d4ae4de044b0fef42a03454ccbe6401a8ac08cac34ec59da20165","cross_cats_sorted":["cs.HC","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T14:25:17Z","title_canon_sha256":"299fe652aac65e7ca26a97f7c12a19da9ce71f154653b6a90da70b08e5ca29f3"},"schema_version":"1.0","source":{"id":"2504.07981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07981","created_at":"2026-07-05T10:47:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07981v1","created_at":"2026-07-05T10:47:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07981","created_at":"2026-07-05T10:47:40Z"},{"alias_kind":"pith_short_12","alias_value":"R6CLSEYLKRE4","created_at":"2026-07-05T10:47:40Z"},{"alias_kind":"pith_short_16","alias_value":"R6CLSEYLKRE42CS5","created_at":"2026-07-05T10:47:40Z"},{"alias_kind":"pith_short_8","alias_value":"R6CLSEYL","created_at":"2026-07-05T10:47:40Z"}],"graph_snapshots":[{"event_id":"sha256:a5612c79748aa2bfa4d0ccb87e322cd5d0fe1d2836e2b4927c1d0f66e318eddd","target":"graph","created_at":"2026-07-05T10:47:40Z","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/2504.07981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Multi-modal Large Language Models (MLLMs) have led to significant progress in developing GUI agents for general tasks such as web browsing and mobile phone use. However, their application in professional domains remains under-explored. These specialized workflows introduce unique challenges for GUI perception models, including high-resolution displays, smaller target sizes, and complex environments. In this paper, we introduce ScreenSpot-Pro, a new benchmark designed to rigorously evaluate the grounding capabilities of MLLMs in high-resolution professional settings. The ","authors_text":"Hongzhan Lin, Jing Ma, Kaixin Li, Tat-Seng Chua, Yuchen Tian, Zhiyong Huang, Ziyang Luo, Ziyang Meng","cross_cats":["cs.HC","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T14:25:17Z","title":"ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07981","kind":"arxiv","version":1},"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":"sha256:94b14b88cd910ba88719604589bf39e211c0f654c70b4a90480185e31117ecf0","target":"record","created_at":"2026-07-05T10:47:40Z","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":"bc2bae133e7d4ae4de044b0fef42a03454ccbe6401a8ac08cac34ec59da20165","cross_cats_sorted":["cs.HC","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T14:25:17Z","title_canon_sha256":"299fe652aac65e7ca26a97f7c12a19da9ce71f154653b6a90da70b08e5ca29f3"},"schema_version":"1.0","source":{"id":"2504.07981","kind":"arxiv","version":1}},"canonical_sha256":"8f84b9130b5449cd0a5d1ca8e90d6a62ebb16ba6889dca4931aec7ba054c33bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f84b9130b5449cd0a5d1ca8e90d6a62ebb16ba6889dca4931aec7ba054c33bc","first_computed_at":"2026-07-05T10:47:40.480567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:40.480567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKavhpP6BvpXdVBvuoJikT08A6+iQ36jSb+NXxATCnS4iMh7T3QRKQYf8UXtsx409tMibXR5ax/8HiMorAXXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:40.481039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07981","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94b14b88cd910ba88719604589bf39e211c0f654c70b4a90480185e31117ecf0","sha256:a5612c79748aa2bfa4d0ccb87e322cd5d0fe1d2836e2b4927c1d0f66e318eddd"],"state_sha256":"9e58b2cc6d64e124b212fdf8564a90f17e0659d3aa371d3370e617fd0a80faee"}