{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TVT562ICSH4VTSILW6MAPZRFZ6","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":"275cda370f40995c0111a61506492bb25399b4d5f2c257e05af24e3e190fe916","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:08Z","title_canon_sha256":"948a943502b88717213b99fa6a3a1c2b2ea6b58f88f20ec657bd5f17b3d03365"},"schema_version":"1.0","source":{"id":"2406.10227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10227","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10227v1","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10227","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"pith_short_12","alias_value":"TVT562ICSH4V","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"pith_short_16","alias_value":"TVT562ICSH4VTSIL","created_at":"2026-07-05T08:32:06Z"},{"alias_kind":"pith_short_8","alias_value":"TVT562IC","created_at":"2026-07-05T08:32:06Z"}],"graph_snapshots":[{"event_id":"sha256:d861023314d0739825f18553dacb278d417811e6d6c0881c47d329ca7521c05a","target":"graph","created_at":"2026-07-05T08:32:06Z","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/2406.10227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Difei Gao, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Mingyi Yan, Qinchen Wu, Zhengyuan Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:08Z","title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10227","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:b52643a93d6b47a1f7bed64d83d6b46ed3903c246b6b8af6a0933dda010938c5","target":"record","created_at":"2026-07-05T08:32:06Z","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":"275cda370f40995c0111a61506492bb25399b4d5f2c257e05af24e3e190fe916","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:08Z","title_canon_sha256":"948a943502b88717213b99fa6a3a1c2b2ea6b58f88f20ec657bd5f17b3d03365"},"schema_version":"1.0","source":{"id":"2406.10227","kind":"arxiv","version":1}},"canonical_sha256":"9d67df690291f959c90bb79807e625cfa7a552a25f10857d4199aa66ca9fc399","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d67df690291f959c90bb79807e625cfa7a552a25f10857d4199aa66ca9fc399","first_computed_at":"2026-07-05T08:32:06.989837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:06.989837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BCvk60RuRK3634MWuXhXcFfe+xqzvrO+YCSXJkaeCPPPSIlowqtKapI1AfdnGb5fEGvwtkqYzcUKBijA+CnvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:06.990324Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b52643a93d6b47a1f7bed64d83d6b46ed3903c246b6b8af6a0933dda010938c5","sha256:d861023314d0739825f18553dacb278d417811e6d6c0881c47d329ca7521c05a"],"state_sha256":"98a601605f6226b9cdff31e477abaeb65d23fe919ec77bdb13a1eaed871072f9"}