{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T5N423WTI5BFJ7AIHJCCOATOPK","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":"77a7eef9d383d60f2df4e728860ff0c0d19c479276a241e55869ed42d4f8c6e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:32:38Z","title_canon_sha256":"dab082cb034df6c7217fc4e6b74a3d0e38ab05b294c30ad5e3e5e3f20d2b10ac"},"schema_version":"1.0","source":{"id":"2608.10042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10042","created_at":"2026-08-12T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10042v1","created_at":"2026-08-12T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10042","created_at":"2026-08-12T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"T5N423WTI5BF","created_at":"2026-08-12T00:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"T5N423WTI5BFJ7AI","created_at":"2026-08-12T00:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"T5N423WT","created_at":"2026-08-12T00:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:87256e2f09090d5114ffcc7580f37a0de570fe5ad6742f9397d45c3d014da5b0","target":"graph","created_at":"2026-08-12T00:22:39Z","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/2608.10042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool use, or response-level personalization. We introduce UserToolBench , a benchmark for personalized decision making in tool-use LLMs. UserToolBench tests whether a model can infer latent user preferences from interaction history, recognize when clarification is needed, and produce user-aligned tool-call trajectories under incomplete information. The benchmark is built from privacy-sanitized real interaction traces and combines structured persona pro","authors_text":"Bin Wang, Jingyuan Yang, Keze Wang, Xuexiong Yin, Yongsen Zheng, Yubin Wang, Yuxiang Zhang, Zechuan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:32:38Z","title":"UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10042","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":"sha256:77fd59b9c04d8acc931fd3d77b63bd168f987bc36e392169066cbc906db753bf","target":"record","created_at":"2026-08-12T00:22:39Z","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":"77a7eef9d383d60f2df4e728860ff0c0d19c479276a241e55869ed42d4f8c6e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:32:38Z","title_canon_sha256":"dab082cb034df6c7217fc4e6b74a3d0e38ab05b294c30ad5e3e5e3f20d2b10ac"},"schema_version":"1.0","source":{"id":"2608.10042","kind":"arxiv","version":1}},"canonical_sha256":"9f5bcd6ed3474254fc083a4427026e7abc53aee74fc358296379d5b7d81f51fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f5bcd6ed3474254fc083a4427026e7abc53aee74fc358296379d5b7d81f51fd","first_computed_at":"2026-08-12T00:22:39.154152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:22:39.154152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dlqY+fPKCNowducsVl2YjsJHtZ0f7n/RVPXnlIzgEYNSo6X4tSoV8B5pKgn9hNTHbdB+Ti+QPPWSVXQbSx8CAg==","signature_status":"signed_v1","signed_at":"2026-08-12T00:22:39.155886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77fd59b9c04d8acc931fd3d77b63bd168f987bc36e392169066cbc906db753bf","sha256:87256e2f09090d5114ffcc7580f37a0de570fe5ad6742f9397d45c3d014da5b0"],"state_sha256":"9862d91223706c5f7972c446c60cf7ba90d047df42a3fc9ab1cd82d19b231fb2"}