{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVT562ICSH4VTSILW6MAPZRFZ6","short_pith_number":"pith:TVT562IC","schema_version":"1.0","canonical_sha256":"9d67df690291f959c90bb79807e625cfa7a552a25f10857d4199aa66ca9fc399","source":{"kind":"arxiv","id":"2406.10227","version":1},"attestation_state":"computed","paper":{"title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Difei Gao, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Mingyi Yan, Qinchen Wu, Zhengyuan Yang","submitted_at":"2024-06-14T17:59:08Z","abstract_excerpt":"Graphical User Interface (GUI) automation holds significant promise for enhancing human productivity by assisting with computer tasks. Existing task formulations primarily focus on simple tasks that can be specified by a single, language-only instruction, such as \"Insert a new slide.\" In this work, we introduce VideoGUI, a novel multi-modal benchmark designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, our benchmark focuses on tasks involving professional and novel software (e.g., Adobe Photoshop or Stable Diffusion WebUI) and com"},"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":"2406.10227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"948a943502b88717213b99fa6a3a1c2b2ea6b58f88f20ec657bd5f17b3d03365","abstract_canon_sha256":"275cda370f40995c0111a61506492bb25399b4d5f2c257e05af24e3e190fe916"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:06.990324Z","signature_b64":"BCvk60RuRK3634MWuXhXcFfe+xqzvrO+YCSXJkaeCPPPSIlowqtKapI1AfdnGb5fEGvwtkqYzcUKBijA+CnvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d67df690291f959c90bb79807e625cfa7a552a25f10857d4199aa66ca9fc399","last_reissued_at":"2026-07-05T08:32:06.989837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:06.989837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Difei Gao, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Mingyi Yan, Qinchen Wu, Zhengyuan Yang","submitted_at":"2024-06-14T17:59:08Z","abstract_excerpt":"Graphical User Interface (GUI) automation holds significant promise for enhancing human productivity by assisting with computer tasks. Existing task formulations primarily focus on simple tasks that can be specified by a single, language-only instruction, such as \"Insert a new slide.\" In this work, we introduce VideoGUI, a novel multi-modal benchmark designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, our benchmark focuses on tasks involving professional and novel software (e.g., Adobe Photoshop or Stable Diffusion WebUI) and com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10227","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/2406.10227/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":"2406.10227","created_at":"2026-07-05T08:32:06.989895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10227v1","created_at":"2026-07-05T08:32:06.989895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10227","created_at":"2026-07-05T08:32:06.989895+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVT562ICSH4V","created_at":"2026-07-05T08:32:06.989895+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVT562ICSH4VTSIL","created_at":"2026-07-05T08:32:06.989895+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVT562IC","created_at":"2026-07-05T08:32:06.989895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04036","citing_title":"PresentAgent: Multimodal Agent for Presentation Video Generation","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6","json":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6.json","graph_json":"https://pith.science/api/pith-number/TVT562ICSH4VTSILW6MAPZRFZ6/graph.json","events_json":"https://pith.science/api/pith-number/TVT562ICSH4VTSILW6MAPZRFZ6/events.json","paper":"https://pith.science/paper/TVT562IC"},"agent_actions":{"view_html":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6","download_json":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6.json","view_paper":"https://pith.science/paper/TVT562IC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10227&json=true","fetch_graph":"https://pith.science/api/pith-number/TVT562ICSH4VTSILW6MAPZRFZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/TVT562ICSH4VTSILW6MAPZRFZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6/action/storage_attestation","attest_author":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6/action/author_attestation","sign_citation":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6/action/citation_signature","submit_replication":"https://pith.science/pith/TVT562ICSH4VTSILW6MAPZRFZ6/action/replication_record"}},"created_at":"2026-07-05T08:32:06.989895+00:00","updated_at":"2026-07-05T08:32:06.989895+00:00"}