{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7UCCR4JR3YWV3GDTMSBDMCOY4","short_pith_number":"pith:Y7UCCR4J","schema_version":"1.0","canonical_sha256":"c7e82147898ef16aecc39b2411b04ec725adedb3d96f10b1802ccd7a57d722fc","source":{"kind":"arxiv","id":"2606.10956","version":1},"attestation_state":"computed","paper":{"title":"Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dongdong Zhang, Furu Wei, Jiayu Ding, Lei Cui, Li Dong, Nan Yang, Shaohan Huang, Tengchao Lv, Wenshan Wu, Xiangyang Zhou, Yilin Jia, Yupan Huang, Yuzhong Zhao","submitted_at":"2026-06-09T14:59:14Z","abstract_excerpt":"The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office automation is an ideal environment for benchmarking document-automation capability, as it requires long-horizon planning and reasoning, precise parameter configuration, and multi-application integration. To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE), featuring 200 comprehensive practical-operation tasks across Word"},"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":"2606.10956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T14:59:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9399dcdce0d6874fba4faf00d9f3e60691b5c6423ed7cf9aa41727448debcc76","abstract_canon_sha256":"3f016c995c01528c728197a357fa50a61da8140b066abab3358cdc968194fbe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:49.990755Z","signature_b64":"1umlXgRR2Jjl/cEAX5CnH/qRRsGzdDWCmRcC406tClDvNDaxN97d/iBPq8N3dVKcMmnBAmGV5YnsfDYZP+sfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7e82147898ef16aecc39b2411b04ec725adedb3d96f10b1802ccd7a57d722fc","last_reissued_at":"2026-06-10T01:10:49.989924Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:49.989924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dongdong Zhang, Furu Wei, Jiayu Ding, Lei Cui, Li Dong, Nan Yang, Shaohan Huang, Tengchao Lv, Wenshan Wu, Xiangyang Zhou, Yilin Jia, Yupan Huang, Yuzhong Zhao","submitted_at":"2026-06-09T14:59:14Z","abstract_excerpt":"The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office automation is an ideal environment for benchmarking document-automation capability, as it requires long-horizon planning and reasoning, precise parameter configuration, and multi-application integration. To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE), featuring 200 comprehensive practical-operation tasks across Word"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10956","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/2606.10956/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":"2606.10956","created_at":"2026-06-10T01:10:49.990068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10956v1","created_at":"2026-06-10T01:10:49.990068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10956","created_at":"2026-06-10T01:10:49.990068+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7UCCR4JR3YW","created_at":"2026-06-10T01:10:49.990068+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7UCCR4JR3YWV3GD","created_at":"2026-06-10T01:10:49.990068+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7UCCR4J","created_at":"2026-06-10T01:10:49.990068+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/Y7UCCR4JR3YWV3GDTMSBDMCOY4","json":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4.json","graph_json":"https://pith.science/api/pith-number/Y7UCCR4JR3YWV3GDTMSBDMCOY4/graph.json","events_json":"https://pith.science/api/pith-number/Y7UCCR4JR3YWV3GDTMSBDMCOY4/events.json","paper":"https://pith.science/paper/Y7UCCR4J"},"agent_actions":{"view_html":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4","download_json":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4.json","view_paper":"https://pith.science/paper/Y7UCCR4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10956&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7UCCR4JR3YWV3GDTMSBDMCOY4/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7UCCR4JR3YWV3GDTMSBDMCOY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4/action/storage_attestation","attest_author":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4/action/author_attestation","sign_citation":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4/action/citation_signature","submit_replication":"https://pith.science/pith/Y7UCCR4JR3YWV3GDTMSBDMCOY4/action/replication_record"}},"created_at":"2026-06-10T01:10:49.990068+00:00","updated_at":"2026-06-10T01:10:49.990068+00:00"}