{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3C2J23RTPBLP5GP7H7T6GWK6HU","short_pith_number":"pith:3C2J23RT","schema_version":"1.0","canonical_sha256":"d8b49d6e337856fe99ff3fe7e3595e3d030521c495b23c9372133a2b33eaa632","source":{"kind":"arxiv","id":"2606.23654","version":1},"attestation_state":"computed","paper":{"title":"EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Che Jiang, Dianqiao Lei, Jincheng Zhong, Junlin Yang, Kai Tian, Kaiyan Zhang, Weizhi Wang, Zhenzhao Yuan","submitted_at":"2026-06-22T17:39:43Z","abstract_excerpt":"Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterprise agent benchmark constructed from proprietary, real-world agent sessions. Starting from a large archive of workplace sessions, the EnterpriseClawBench produces 852 reproducible tasks, each paired with recovered fixtures, rewritten prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Because the sessions contain internal enterprise content, we do not release the benchmark data; instead, our reu"},"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":"2606.23654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T17:39:43Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"38a2a96d728b5e6a79dd6c5ea8b4e5db88c7ce9e668f38233d871ee51f300953","abstract_canon_sha256":"3d97d186423868f72e23d569b4cb2c70994ac5f048d1a1324bdc3ad892d8d9a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:33.810018Z","signature_b64":"t447RfMw6vSY/0CHFXfVaHco9DHOzwE8JKkYrEO6jqHMdogC8BU/AB/nqkeC1ulrzHp9+CM/unohKBoWqZpPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b49d6e337856fe99ff3fe7e3595e3d030521c495b23c9372133a2b33eaa632","last_reissued_at":"2026-06-23T03:14:33.809585Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:33.809585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Che Jiang, Dianqiao Lei, Jincheng Zhong, Junlin Yang, Kai Tian, Kaiyan Zhang, Weizhi Wang, Zhenzhao Yuan","submitted_at":"2026-06-22T17:39:43Z","abstract_excerpt":"Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterprise agent benchmark constructed from proprietary, real-world agent sessions. Starting from a large archive of workplace sessions, the EnterpriseClawBench produces 852 reproducible tasks, each paired with recovered fixtures, rewritten prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Because the sessions contain internal enterprise content, we do not release the benchmark data; instead, our reu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23654","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/2606.23654/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":"2606.23654","created_at":"2026-06-23T03:14:33.809645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23654v1","created_at":"2026-06-23T03:14:33.809645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23654","created_at":"2026-06-23T03:14:33.809645+00:00"},{"alias_kind":"pith_short_12","alias_value":"3C2J23RTPBLP","created_at":"2026-06-23T03:14:33.809645+00:00"},{"alias_kind":"pith_short_16","alias_value":"3C2J23RTPBLP5GP7","created_at":"2026-06-23T03:14:33.809645+00:00"},{"alias_kind":"pith_short_8","alias_value":"3C2J23RT","created_at":"2026-06-23T03:14:33.809645+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/3C2J23RTPBLP5GP7H7T6GWK6HU","json":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU.json","graph_json":"https://pith.science/api/pith-number/3C2J23RTPBLP5GP7H7T6GWK6HU/graph.json","events_json":"https://pith.science/api/pith-number/3C2J23RTPBLP5GP7H7T6GWK6HU/events.json","paper":"https://pith.science/paper/3C2J23RT"},"agent_actions":{"view_html":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU","download_json":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU.json","view_paper":"https://pith.science/paper/3C2J23RT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23654&json=true","fetch_graph":"https://pith.science/api/pith-number/3C2J23RTPBLP5GP7H7T6GWK6HU/graph.json","fetch_events":"https://pith.science/api/pith-number/3C2J23RTPBLP5GP7H7T6GWK6HU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU/action/storage_attestation","attest_author":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU/action/author_attestation","sign_citation":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU/action/citation_signature","submit_replication":"https://pith.science/pith/3C2J23RTPBLP5GP7H7T6GWK6HU/action/replication_record"}},"created_at":"2026-06-23T03:14:33.809645+00:00","updated_at":"2026-06-23T03:14:33.809645+00:00"}