{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6DMB5TESJZJRYZQSD67KV6UV64","short_pith_number":"pith:6DMB5TES","schema_version":"1.0","canonical_sha256":"f0d81ecc924e531c66121fbeaafa95f733f9c804dd028fb245a201f9b82fdf8a","source":{"kind":"arxiv","id":"2607.27155","version":1},"attestation_state":"computed","paper":{"title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Chang Gao, Hua Wu, Jingbo Zhou, Jingjia Cao, Kaiqi Guo, Le Zhang, Mingxuan Li, Muxin Guo, Qi Bao, Xinjiang Lu, Yanru Ma, Yixiong Xiao, Yusai Zhao, Zenghui Zhang, Zhenghai Chen","submitted_at":"2026-07-29T17:33:47Z","abstract_excerpt":"Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An "},"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":"2607.27155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T17:33:47Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"35f798e503ac6e95e090e48a17b33526224947443ea89c307e306069ce92d722","abstract_canon_sha256":"245b9607febb01c18a87a089d5fd8c477cfb0a39faf4209b335e71638bff3e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d81ecc924e531c66121fbeaafa95f733f9c804dd028fb245a201f9b82fdf8a","last_reissued_at":"2026-07-30T01:23:54.246141Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:54.246141Z"},"graph_snapshot":{"paper":{"title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Chang Gao, Hua Wu, Jingbo Zhou, Jingjia Cao, Kaiqi Guo, Le Zhang, Mingxuan Li, Muxin Guo, Qi Bao, Xinjiang Lu, Yanru Ma, Yixiong Xiao, Yusai Zhao, Zenghui Zhang, Zhenghai Chen","submitted_at":"2026-07-29T17:33:47Z","abstract_excerpt":"Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27155","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/2607.27155/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":"2607.27155","created_at":"2026-07-30T01:23:54.251063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27155v1","created_at":"2026-07-30T01:23:54.251063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27155","created_at":"2026-07-30T01:23:54.251063+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DMB5TESJZJR","created_at":"2026-07-30T01:23:54.251063+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DMB5TESJZJRYZQS","created_at":"2026-07-30T01:23:54.251063+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DMB5TES","created_at":"2026-07-30T01:23:54.251063+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/6DMB5TESJZJRYZQSD67KV6UV64","json":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64.json","graph_json":"https://pith.science/api/pith-number/6DMB5TESJZJRYZQSD67KV6UV64/graph.json","events_json":"https://pith.science/api/pith-number/6DMB5TESJZJRYZQSD67KV6UV64/events.json","paper":"https://pith.science/paper/6DMB5TES"},"agent_actions":{"view_html":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64","download_json":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64.json","view_paper":"https://pith.science/paper/6DMB5TES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27155&json=true","fetch_graph":"https://pith.science/api/pith-number/6DMB5TESJZJRYZQSD67KV6UV64/graph.json","fetch_events":"https://pith.science/api/pith-number/6DMB5TESJZJRYZQSD67KV6UV64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64/action/storage_attestation","attest_author":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64/action/author_attestation","sign_citation":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64/action/citation_signature","submit_replication":"https://pith.science/pith/6DMB5TESJZJRYZQSD67KV6UV64/action/replication_record"}},"created_at":"2026-07-30T01:23:54.251063+00:00","updated_at":"2026-07-30T01:23:54.251063+00:00"}