{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WD4PEKNZUUCJJGCODL3BYIOC26","short_pith_number":"pith:WD4PEKNZ","schema_version":"1.0","canonical_sha256":"b0f8f229b9a50494984e1af61c21c2d78c3769f95a03fc7f0536d1f4a96af8c1","source":{"kind":"arxiv","id":"2606.31174","version":1},"attestation_state":"computed","paper":{"title":"ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cihang Xie, Haonian Ji, Huaxiu Yao, Kaiwen Xiong, Shi Qiu, Xinyu Ye, Zeyu Zheng","submitted_at":"2026-06-30T06:06:08Z","abstract_excerpt":"Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows. Whether one model can actually run such a team is largely unmeasured: existing benchmarks score a policy's own task-solving or a fixed multi-agent system's emergent behavior, but none isolate the management ability of the single LLM acting as leader. We introduce ClawArena-Team, a benchmark of 41 multi-turn, multimodal, multi-directory scena"},"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":"2606.31174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T06:06:08Z","cross_cats_sorted":[],"title_canon_sha256":"c5d6ab653a16f3b953c8a7741328ea5fdbdac20a86b2f4d334fa60510897c25f","abstract_canon_sha256":"4ae34b19129370f4c0262a226bc1b9c4fe8ab7f7a1b413f7af66e1fc135f35d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:31.177892Z","signature_b64":"URiCiLUvGZT+MOe/aKVb+2gZUuclDL947EzGKBGJ2dtFQG+BqxXdFcm/h/bRbx7ak9QPsT2kLWb9t1M5+qihBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f8f229b9a50494984e1af61c21c2d78c3769f95a03fc7f0536d1f4a96af8c1","last_reissued_at":"2026-07-01T01:17:31.177514Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:31.177514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cihang Xie, Haonian Ji, Huaxiu Yao, Kaiwen Xiong, Shi Qiu, Xinyu Ye, Zeyu Zheng","submitted_at":"2026-06-30T06:06:08Z","abstract_excerpt":"Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows. Whether one model can actually run such a team is largely unmeasured: existing benchmarks score a policy's own task-solving or a fixed multi-agent system's emergent behavior, but none isolate the management ability of the single LLM acting as leader. We introduce ClawArena-Team, a benchmark of 41 multi-turn, multimodal, multi-directory scena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31174","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/2606.31174/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":"2606.31174","created_at":"2026-07-01T01:17:31.177570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31174v1","created_at":"2026-07-01T01:17:31.177570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31174","created_at":"2026-07-01T01:17:31.177570+00:00"},{"alias_kind":"pith_short_12","alias_value":"WD4PEKNZUUCJ","created_at":"2026-07-01T01:17:31.177570+00:00"},{"alias_kind":"pith_short_16","alias_value":"WD4PEKNZUUCJJGCO","created_at":"2026-07-01T01:17:31.177570+00:00"},{"alias_kind":"pith_short_8","alias_value":"WD4PEKNZ","created_at":"2026-07-01T01:17:31.177570+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/WD4PEKNZUUCJJGCODL3BYIOC26","json":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26.json","graph_json":"https://pith.science/api/pith-number/WD4PEKNZUUCJJGCODL3BYIOC26/graph.json","events_json":"https://pith.science/api/pith-number/WD4PEKNZUUCJJGCODL3BYIOC26/events.json","paper":"https://pith.science/paper/WD4PEKNZ"},"agent_actions":{"view_html":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26","download_json":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26.json","view_paper":"https://pith.science/paper/WD4PEKNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31174&json=true","fetch_graph":"https://pith.science/api/pith-number/WD4PEKNZUUCJJGCODL3BYIOC26/graph.json","fetch_events":"https://pith.science/api/pith-number/WD4PEKNZUUCJJGCODL3BYIOC26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26/action/storage_attestation","attest_author":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26/action/author_attestation","sign_citation":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26/action/citation_signature","submit_replication":"https://pith.science/pith/WD4PEKNZUUCJJGCODL3BYIOC26/action/replication_record"}},"created_at":"2026-07-01T01:17:31.177570+00:00","updated_at":"2026-07-01T01:17:31.177570+00:00"}