{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WMCX4AC4YMR2BN64DES6JZYTBV","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":"08cda773538a5e55d07b05c5b54a5eb020efce52c3d5b7bb38998033a14a77ec","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-21T15:32:57Z","title_canon_sha256":"57f9bcb1b8852b9f399cd9abc9ef2257c1edfcfaaf1e81d7eb84204548c408c9"},"schema_version":"1.0","source":{"id":"2606.22557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22557","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22557v1","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22557","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"WMCX4AC4YMR2","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"pith_short_16","alias_value":"WMCX4AC4YMR2BN64","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"pith_short_8","alias_value":"WMCX4AC4","created_at":"2026-06-23T02:13:41Z"}],"graph_snapshots":[{"event_id":"sha256:3ab05c960ebc88c76b6f80f570d3deb83fcf9946f80bba9c61563b7acfa2135f","target":"graph","created_at":"2026-06-23T02:13:41Z","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/2606.22557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer use agents (CUAs) have advanced rapidly in desktop automation, and a growing number of users deploy CUAs such as OpenClaw on Mac Mini for always-on automation. However, existing benchmarks, including those for macOS, evaluate agents without framework augmentation and rely on binary evaluation. As a result, they fail to capture both the framework capabilities leveraged by modern CUAs and the partial progress on long-horizon, multi-application tasks. We present MacAgentBench, a comprehensive macOS agent benchmark comprising 676 tasks across 25 applications, with nearly 60% involving bot","authors_text":"Biqing Qi, Bowen Fu, Bowen Yang, Bowen Zhou, Shijie Wang, Shuang Cheng, Xiaowei Sun, Yibo Zhao, Yikun Fu, Zehao Li, Zhenyu Wu, Zhoumianze Liu, Zichen Ding","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-21T15:32:57Z","title":"MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22557","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:af15f10905c04a5d5747281b01904b0a1532082fae228d1937e0be45adc59d50","target":"record","created_at":"2026-06-23T02:13:41Z","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":"08cda773538a5e55d07b05c5b54a5eb020efce52c3d5b7bb38998033a14a77ec","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-21T15:32:57Z","title_canon_sha256":"57f9bcb1b8852b9f399cd9abc9ef2257c1edfcfaaf1e81d7eb84204548c408c9"},"schema_version":"1.0","source":{"id":"2606.22557","kind":"arxiv","version":1}},"canonical_sha256":"b3057e005cc323a0b7dc1925e4e7130d5878a9407ee24112b1cd0e450ad20a8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3057e005cc323a0b7dc1925e4e7130d5878a9407ee24112b1cd0e450ad20a8d","first_computed_at":"2026-06-23T02:13:41.535327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:41.535327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MSrSRPjwjuQcfGDn8H8/iW2hMa51lmFhfQnQTGhV4eiXvqhMG82Ve66N3eXluAxDhghp4SHpSbRJcFgy03d3Bw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:41.535745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af15f10905c04a5d5747281b01904b0a1532082fae228d1937e0be45adc59d50","sha256:3ab05c960ebc88c76b6f80f570d3deb83fcf9946f80bba9c61563b7acfa2135f"],"state_sha256":"1336c1e17c177cfdcac503e8013db4694a0e694d45dbc46b05d81326d8473290"}