{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3VNJ757FPPHA54ZRDFYKYNCRI5","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":"41d50c36631e8051e0cb569d472528ac5882b869a46555ae6d6d659cea0fb338","cross_cats_sorted":["cs.LG","cs.OS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-19T05:26:40Z","title_canon_sha256":"ef24f2fd4ebdb95284a96160d79711c411024a1424e19a2060f60e311b5432a5"},"schema_version":"1.0","source":{"id":"2506.16042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16042","created_at":"2026-05-20T00:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16042v2","created_at":"2026-05-20T00:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16042","created_at":"2026-05-20T00:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"3VNJ757FPPHA","created_at":"2026-05-20T00:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"3VNJ757FPPHA54ZR","created_at":"2026-05-20T00:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"3VNJ757F","created_at":"2026-05-20T00:05:30Z"}],"graph_snapshots":[{"event_id":"sha256:5eb1409f5c2ae043094383d89bf29b1c21c92090fac58e673ee7c02377b85841","target":"graph","created_at":"2026-05-20T00:05:30Z","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/2506.16042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative AI is being leveraged to solve a variety of computer-use tasks involving desktop applications. State-of-the-art systems have focused solely on improving accuracy on leading benchmarks. However, these systems are practically unusable due to extremely high end-to-end latency (e.g., tens of minutes) for tasks that typically take humans just a few minutes to complete. To understand the cause behind this and to guide future developments of computer agents, we conduct the first study on the temporal performance of computer-use agents on OSWorld, the flagship benchmark in computer-use AI. ","authors_text":"Qi Qi, Reyna Abhyankar, Yiying Zhang","cross_cats":["cs.LG","cs.OS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-19T05:26:40Z","title":"OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16042","kind":"arxiv","version":2},"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":"sha256:55d3ab818f4d942d6263460633cfd354f72dc907411dc799c0fa67e8483b069c","target":"record","created_at":"2026-05-20T00:05:30Z","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":"41d50c36631e8051e0cb569d472528ac5882b869a46555ae6d6d659cea0fb338","cross_cats_sorted":["cs.LG","cs.OS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-19T05:26:40Z","title_canon_sha256":"ef24f2fd4ebdb95284a96160d79711c411024a1424e19a2060f60e311b5432a5"},"schema_version":"1.0","source":{"id":"2506.16042","kind":"arxiv","version":2}},"canonical_sha256":"dd5a9ff7e57bce0ef3311970ac3451476ea4c95199368ca3f6536284cbc1de67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd5a9ff7e57bce0ef3311970ac3451476ea4c95199368ca3f6536284cbc1de67","first_computed_at":"2026-05-20T00:05:30.364428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:30.364428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"74S3lq1LNE76ekV8Ehb8sULgw0K68m67UE7X6KZd7dhgxZ7BvFuebps/yopJzWkoDkuChprKQex5mqcji2AgCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:30.365222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55d3ab818f4d942d6263460633cfd354f72dc907411dc799c0fa67e8483b069c","sha256:5eb1409f5c2ae043094383d89bf29b1c21c92090fac58e673ee7c02377b85841"],"state_sha256":"418d579fd72940cd990e18a8addc89e1ca63dd25814b5ce803f8777383a106aa"}