{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AHCVTNHJW7HFPFXJ7OZFWL54XQ","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":"250bb573fb777ec86332c2912f51bf2e9c4e9e7b85896e96511bc67cbeb2b53b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T08:28:37Z","title_canon_sha256":"b627a07e74d4f2d6fe2dc39f2e20b360527def0ae9851dad34b08c07f2f5ee58"},"schema_version":"1.0","source":{"id":"2606.03318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03318","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03318v1","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03318","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"AHCVTNHJW7HF","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"AHCVTNHJW7HFPFXJ","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"AHCVTNHJ","created_at":"2026-06-03T01:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:d397f9d076eaa8fb7cf53bc7d8dcfde7185afc208f3769d1ba711624b22e5f1f","target":"graph","created_at":"2026-06-03T01:05:54Z","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/2606.03318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks mostly rely on simulated idealized user assumptions and lacks experience-oriented evaluation. These limitations fail to account for the ambiguity, uncooperative behaviors, and shifting intentions characteristic of real-world users. To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios. RUT-Bench supports high-fidelity simulations cove","authors_text":"Chunxiao Liu, Hao Xu, Hongsheng Xin, Kaike Zhang, Ning Miao, Tingfeng Hui, Xuan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T08:28:37Z","title":"Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03318","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":"sha256:9b1efdc6790ac26430aaf6b329344fc1a281117abbdf9bae5b54090ed8efe15d","target":"record","created_at":"2026-06-03T01:05:54Z","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":"250bb573fb777ec86332c2912f51bf2e9c4e9e7b85896e96511bc67cbeb2b53b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T08:28:37Z","title_canon_sha256":"b627a07e74d4f2d6fe2dc39f2e20b360527def0ae9851dad34b08c07f2f5ee58"},"schema_version":"1.0","source":{"id":"2606.03318","kind":"arxiv","version":1}},"canonical_sha256":"01c559b4e9b7ce5796e9fbb25b2fbcbc1d05b6835a1b27425d56d7147f90809a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01c559b4e9b7ce5796e9fbb25b2fbcbc1d05b6835a1b27425d56d7147f90809a","first_computed_at":"2026-06-03T01:05:54.849233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:54.849233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qEJwMXqrMueJFGoliwRks/KEcEDYNSs+AcugKv4y5EGqV/1l7z60CZ5Oz0G6LYN+3VyHpMWJpxq0g+3h3SpYDQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:54.849728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b1efdc6790ac26430aaf6b329344fc1a281117abbdf9bae5b54090ed8efe15d","sha256:d397f9d076eaa8fb7cf53bc7d8dcfde7185afc208f3769d1ba711624b22e5f1f"],"state_sha256":"3b01a6efe344165c8b8e940fe6196355193d87e121bfb8ef56a2d16727160c35"}