{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UA54UX4BJ7I36TJDHDQUYMZ5YF","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":"5cc32bb290e7c6e269b75e305a5b8a92b6fd86c256f51d768bcb5cdc77873752","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:39:23Z","title_canon_sha256":"f0cb370316715e1687c99fe5fd9906291e9bfbcc694223bf013f0d20abf2e862"},"schema_version":"1.0","source":{"id":"2606.09426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09426","created_at":"2026-06-09T02:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09426v1","created_at":"2026-06-09T02:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09426","created_at":"2026-06-09T02:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"UA54UX4BJ7I3","created_at":"2026-06-09T02:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"UA54UX4BJ7I36TJD","created_at":"2026-06-09T02:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"UA54UX4B","created_at":"2026-06-09T02:08:47Z"}],"graph_snapshots":[{"event_id":"sha256:3e14d52ac7ef24c57e3b4413e58d8ad0dc70cf7f30d0f33d3255c9659e018833","target":"graph","created_at":"2026-06-09T02:08:47Z","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/2606.09426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce WeaveBench, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within","authors_text":"Bowen Zhou, Caihua Shan, Dongsheng Li, Wanli Li, Yifan Yang, Yunyao Yu, Zhou Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:39:23Z","title":"WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09426","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:b9682f4505472ce7b47d17bcbbebd6cd49e92b7ff2e946222748e5b4740f5370","target":"record","created_at":"2026-06-09T02:08:47Z","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":"5cc32bb290e7c6e269b75e305a5b8a92b6fd86c256f51d768bcb5cdc77873752","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:39:23Z","title_canon_sha256":"f0cb370316715e1687c99fe5fd9906291e9bfbcc694223bf013f0d20abf2e862"},"schema_version":"1.0","source":{"id":"2606.09426","kind":"arxiv","version":1}},"canonical_sha256":"a03bca5f814fd1bf4d2338e14c333dc155475d4461cf47d092f376c6c3df000d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a03bca5f814fd1bf4d2338e14c333dc155475d4461cf47d092f376c6c3df000d","first_computed_at":"2026-06-09T02:08:47.710181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:47.710181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cl3bk3+4hG3+TFSAaUWr/IoNB2PksiMJC1n4bdEFntBjvQS4nVVLRGySLIb2iACzQyYpPJG7RpOkEegOJsQPDg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:47.710991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9682f4505472ce7b47d17bcbbebd6cd49e92b7ff2e946222748e5b4740f5370","sha256:3e14d52ac7ef24c57e3b4413e58d8ad0dc70cf7f30d0f33d3255c9659e018833"],"state_sha256":"463521b60f02d5655902b48409085c33a5832be51fd9bb8c6103c95325b93130"}