{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6DMB5TESJZJRYZQSD67KV6UV64","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"245b9607febb01c18a87a089d5fd8c477cfb0a39faf4209b335e71638bff3e74","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T17:33:47Z","title_canon_sha256":"35f798e503ac6e95e090e48a17b33526224947443ea89c307e306069ce92d722"},"schema_version":"1.0","source":{"id":"2607.27155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27155","created_at":"2026-07-30T01:23:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27155v1","created_at":"2026-07-30T01:23:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27155","created_at":"2026-07-30T01:23:54Z"},{"alias_kind":"pith_short_12","alias_value":"6DMB5TESJZJR","created_at":"2026-07-30T01:23:54Z"},{"alias_kind":"pith_short_16","alias_value":"6DMB5TESJZJRYZQS","created_at":"2026-07-30T01:23:54Z"},{"alias_kind":"pith_short_8","alias_value":"6DMB5TES","created_at":"2026-07-30T01:23:54Z"}],"graph_snapshots":[{"event_id":"sha256:c7eb48af367b9e55a2f2493aca68e473881fa2ab2a05203898e345a7dfc326c9","target":"graph","created_at":"2026-07-30T01:23:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.27155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T17:33:47Z","title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27155","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a6cde340773a55fb3affa91ff468ac6d290636b28e7a909a2a4a0b4afbab874f","target":"record","created_at":"2026-07-30T01:23:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"245b9607febb01c18a87a089d5fd8c477cfb0a39faf4209b335e71638bff3e74","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T17:33:47Z","title_canon_sha256":"35f798e503ac6e95e090e48a17b33526224947443ea89c307e306069ce92d722"},"schema_version":"1.0","source":{"id":"2607.27155","kind":"arxiv","version":1}},"canonical_sha256":"f0d81ecc924e531c66121fbeaafa95f733f9c804dd028fb245a201f9b82fdf8a","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0d81ecc924e531c66121fbeaafa95f733f9c804dd028fb245a201f9b82fdf8a","first_computed_at":"2026-07-30T01:23:54.246141Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:54.246141Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6cde340773a55fb3affa91ff468ac6d290636b28e7a909a2a4a0b4afbab874f","sha256:c7eb48af367b9e55a2f2493aca68e473881fa2ab2a05203898e345a7dfc326c9"],"state_sha256":"de249e2934c2d49eaf57f7dd8077b5e0f70ef433a6fd6e09cccd8ca514a160d8"}