{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UA54UX4BJ7I36TJDHDQUYMZ5YF","short_pith_number":"pith:UA54UX4B","schema_version":"1.0","canonical_sha256":"a03bca5f814fd1bf4d2338e14c333dc155475d4461cf47d092f376c6c3df000d","source":{"kind":"arxiv","id":"2606.09426","version":1},"attestation_state":"computed","paper":{"title":"WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Zhou, Caihua Shan, Dongsheng Li, Wanli Li, Yifan Yang, Yunyao Yu, Zhou Xu","submitted_at":"2026-06-08T12:39:23Z","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"},"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":"2606.09426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:39:23Z","cross_cats_sorted":[],"title_canon_sha256":"f0cb370316715e1687c99fe5fd9906291e9bfbcc694223bf013f0d20abf2e862","abstract_canon_sha256":"5cc32bb290e7c6e269b75e305a5b8a92b6fd86c256f51d768bcb5cdc77873752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:47.710991Z","signature_b64":"Cl3bk3+4hG3+TFSAaUWr/IoNB2PksiMJC1n4bdEFntBjvQS4nVVLRGySLIb2iACzQyYpPJG7RpOkEegOJsQPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a03bca5f814fd1bf4d2338e14c333dc155475d4461cf47d092f376c6c3df000d","last_reissued_at":"2026-06-09T02:08:47.710181Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:47.710181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Zhou, Caihua Shan, Dongsheng Li, Wanli Li, Yifan Yang, Yunyao Yu, Zhou Xu","submitted_at":"2026-06-08T12:39:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09426","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/2606.09426/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":"2606.09426","created_at":"2026-06-09T02:08:47.710298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09426v1","created_at":"2026-06-09T02:08:47.710298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09426","created_at":"2026-06-09T02:08:47.710298+00:00"},{"alias_kind":"pith_short_12","alias_value":"UA54UX4BJ7I3","created_at":"2026-06-09T02:08:47.710298+00:00"},{"alias_kind":"pith_short_16","alias_value":"UA54UX4BJ7I36TJD","created_at":"2026-06-09T02:08:47.710298+00:00"},{"alias_kind":"pith_short_8","alias_value":"UA54UX4B","created_at":"2026-06-09T02:08:47.710298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF","json":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF.json","graph_json":"https://pith.science/api/pith-number/UA54UX4BJ7I36TJDHDQUYMZ5YF/graph.json","events_json":"https://pith.science/api/pith-number/UA54UX4BJ7I36TJDHDQUYMZ5YF/events.json","paper":"https://pith.science/paper/UA54UX4B"},"agent_actions":{"view_html":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF","download_json":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF.json","view_paper":"https://pith.science/paper/UA54UX4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09426&json=true","fetch_graph":"https://pith.science/api/pith-number/UA54UX4BJ7I36TJDHDQUYMZ5YF/graph.json","fetch_events":"https://pith.science/api/pith-number/UA54UX4BJ7I36TJDHDQUYMZ5YF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF/action/storage_attestation","attest_author":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF/action/author_attestation","sign_citation":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF/action/citation_signature","submit_replication":"https://pith.science/pith/UA54UX4BJ7I36TJDHDQUYMZ5YF/action/replication_record"}},"created_at":"2026-06-09T02:08:47.710298+00:00","updated_at":"2026-06-09T02:08:47.710298+00:00"}