{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T5N423WTI5BFJ7AIHJCCOATOPK","short_pith_number":"pith:T5N423WT","schema_version":"1.0","canonical_sha256":"9f5bcd6ed3474254fc083a4427026e7abc53aee74fc358296379d5b7d81f51fd","source":{"kind":"arxiv","id":"2608.10042","version":1},"attestation_state":"computed","paper":{"title":"UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Wang, Jingyuan Yang, Keze Wang, Xuexiong Yin, Yongsen Zheng, Yubin Wang, Yuxiang Zhang, Zechuan Chen","submitted_at":"2026-08-10T09:32:38Z","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"},"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":"2608.10042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:32:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dab082cb034df6c7217fc4e6b74a3d0e38ab05b294c30ad5e3e5e3f20d2b10ac","abstract_canon_sha256":"77a7eef9d383d60f2df4e728860ff0c0d19c479276a241e55869ed42d4f8c6e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:22:39.155886Z","signature_b64":"dlqY+fPKCNowducsVl2YjsJHtZ0f7n/RVPXnlIzgEYNSo6X4tSoV8B5pKgn9hNTHbdB+Ti+QPPWSVXQbSx8CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f5bcd6ed3474254fc083a4427026e7abc53aee74fc358296379d5b7d81f51fd","last_reissued_at":"2026-08-12T00:22:39.154152Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:22:39.154152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Wang, Jingyuan Yang, Keze Wang, Xuexiong Yin, Yongsen Zheng, Yubin Wang, Yuxiang Zhang, Zechuan Chen","submitted_at":"2026-08-10T09:32:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10042","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/2608.10042/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":"2608.10042","created_at":"2026-08-12T00:22:39.156938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10042v1","created_at":"2026-08-12T00:22:39.156938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10042","created_at":"2026-08-12T00:22:39.156938+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5N423WTI5BF","created_at":"2026-08-12T00:22:39.156938+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5N423WTI5BFJ7AI","created_at":"2026-08-12T00:22:39.156938+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5N423WT","created_at":"2026-08-12T00:22:39.156938+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/T5N423WTI5BFJ7AIHJCCOATOPK","json":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK.json","graph_json":"https://pith.science/api/pith-number/T5N423WTI5BFJ7AIHJCCOATOPK/graph.json","events_json":"https://pith.science/api/pith-number/T5N423WTI5BFJ7AIHJCCOATOPK/events.json","paper":"https://pith.science/paper/T5N423WT"},"agent_actions":{"view_html":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK","download_json":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK.json","view_paper":"https://pith.science/paper/T5N423WT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10042&json=true","fetch_graph":"https://pith.science/api/pith-number/T5N423WTI5BFJ7AIHJCCOATOPK/graph.json","fetch_events":"https://pith.science/api/pith-number/T5N423WTI5BFJ7AIHJCCOATOPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK/action/storage_attestation","attest_author":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK/action/author_attestation","sign_citation":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK/action/citation_signature","submit_replication":"https://pith.science/pith/T5N423WTI5BFJ7AIHJCCOATOPK/action/replication_record"}},"created_at":"2026-08-12T00:22:39.156938+00:00","updated_at":"2026-08-12T00:22:39.156938+00:00"}