{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FYD6Z55KTODIUGRTYN4D533QR2","short_pith_number":"pith:FYD6Z55K","schema_version":"1.0","canonical_sha256":"2e07ecf7aa9b868a1a33c3783eef708e9f37db34097be17fc2ca5b679cce8cc5","source":{"kind":"arxiv","id":"2503.11170","version":1},"attestation_state":"computed","paper":{"title":"DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Chen, Hua Wang, Liang Yang, Yaohua Tang, Yibin Xu, Zhi Chen","submitted_at":"2025-03-14T08:16:02Z","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"},"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":"2503.11170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T08:16:02Z","cross_cats_sorted":[],"title_canon_sha256":"fe4ac2e48ce1c5d414015f9b396a410a29eb094f19f1f6381ad117651d0cbac9","abstract_canon_sha256":"58dcdf07f425b43ef49cc608ecd5dde69d9a166c9f5f14fec974baea7099ab4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:13.455303Z","signature_b64":"cMYUiUbb4Or9Cl0fb3qTT3RXsqMl9otIj1yyWz1K7kySKFtRaaBVsVBQ2H80/fE70AF5ZV/tMflo9MFEbxfnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e07ecf7aa9b868a1a33c3783eef708e9f37db34097be17fc2ca5b679cce8cc5","last_reissued_at":"2026-07-05T10:31:13.454809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:13.454809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Chen, Hua Wang, Liang Yang, Yaohua Tang, Yibin Xu, Zhi Chen","submitted_at":"2025-03-14T08:16:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11170","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/2503.11170/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":"2503.11170","created_at":"2026-07-05T10:31:13.454864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11170v1","created_at":"2026-07-05T10:31:13.454864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11170","created_at":"2026-07-05T10:31:13.454864+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYD6Z55KTODI","created_at":"2026-07-05T10:31:13.454864+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYD6Z55KTODIUGRT","created_at":"2026-07-05T10:31:13.454864+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYD6Z55K","created_at":"2026-07-05T10:31:13.454864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07505","citing_title":"LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2","json":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2.json","graph_json":"https://pith.science/api/pith-number/FYD6Z55KTODIUGRTYN4D533QR2/graph.json","events_json":"https://pith.science/api/pith-number/FYD6Z55KTODIUGRTYN4D533QR2/events.json","paper":"https://pith.science/paper/FYD6Z55K"},"agent_actions":{"view_html":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2","download_json":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2.json","view_paper":"https://pith.science/paper/FYD6Z55K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11170&json=true","fetch_graph":"https://pith.science/api/pith-number/FYD6Z55KTODIUGRTYN4D533QR2/graph.json","fetch_events":"https://pith.science/api/pith-number/FYD6Z55KTODIUGRTYN4D533QR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2/action/storage_attestation","attest_author":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2/action/author_attestation","sign_citation":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2/action/citation_signature","submit_replication":"https://pith.science/pith/FYD6Z55KTODIUGRTYN4D533QR2/action/replication_record"}},"created_at":"2026-07-05T10:31:13.454864+00:00","updated_at":"2026-07-05T10:31:13.454864+00:00"}