{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FYD6Z55KTODIUGRTYN4D533QR2","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":"58dcdf07f425b43ef49cc608ecd5dde69d9a166c9f5f14fec974baea7099ab4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T08:16:02Z","title_canon_sha256":"fe4ac2e48ce1c5d414015f9b396a410a29eb094f19f1f6381ad117651d0cbac9"},"schema_version":"1.0","source":{"id":"2503.11170","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11170","created_at":"2026-07-05T10:31:13Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11170v1","created_at":"2026-07-05T10:31:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11170","created_at":"2026-07-05T10:31:13Z"},{"alias_kind":"pith_short_12","alias_value":"FYD6Z55KTODI","created_at":"2026-07-05T10:31:13Z"},{"alias_kind":"pith_short_16","alias_value":"FYD6Z55KTODIUGRT","created_at":"2026-07-05T10:31:13Z"},{"alias_kind":"pith_short_8","alias_value":"FYD6Z55K","created_at":"2026-07-05T10:31:13Z"}],"graph_snapshots":[{"event_id":"sha256:327105aacdba25de5a76806433c40c4b6759035c07b6f27c79259ddefcc8cdf2","target":"graph","created_at":"2026-07-05T10:31:13Z","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/2503.11170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The limitation of graphical user interface (GUI) data has been a significant barrier to the development of GUI agents today, especially for the desktop / computer use scenarios. To address this, we propose an automated GUI data generation pipeline, AutoCaptioner, which generates data with rich descriptions while minimizing human effort. Using AutoCaptioner, we created a novel large-scale desktop GUI dataset, DeskVision, along with the largest desktop test benchmark, DeskVision-Eval, which reflects daily usage and covers diverse systems and UI elements, each with rich descriptions. With DeskVis","authors_text":"Hao Chen, Hua Wang, Liang Yang, Yaohua Tang, Yibin Xu, Zhi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T08:16:02Z","title":"DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11170","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":"sha256:3d412d60ae73f4e6ddffad8e94c9de326523d2eea191f52e30d2b0df48c4e802","target":"record","created_at":"2026-07-05T10:31:13Z","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":"58dcdf07f425b43ef49cc608ecd5dde69d9a166c9f5f14fec974baea7099ab4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T08:16:02Z","title_canon_sha256":"fe4ac2e48ce1c5d414015f9b396a410a29eb094f19f1f6381ad117651d0cbac9"},"schema_version":"1.0","source":{"id":"2503.11170","kind":"arxiv","version":1}},"canonical_sha256":"2e07ecf7aa9b868a1a33c3783eef708e9f37db34097be17fc2ca5b679cce8cc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e07ecf7aa9b868a1a33c3783eef708e9f37db34097be17fc2ca5b679cce8cc5","first_computed_at":"2026-07-05T10:31:13.454809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:13.454809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cMYUiUbb4Or9Cl0fb3qTT3RXsqMl9otIj1yyWz1K7kySKFtRaaBVsVBQ2H80/fE70AF5ZV/tMflo9MFEbxfnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:13.455303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11170","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d412d60ae73f4e6ddffad8e94c9de326523d2eea191f52e30d2b0df48c4e802","sha256:327105aacdba25de5a76806433c40c4b6759035c07b6f27c79259ddefcc8cdf2"],"state_sha256":"4eb279b14805f031f930ec8f6c2c1c759b67f74a470aa93d1984f5d22a94b04b"}