{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AHCVTNHJW7HFPFXJ7OZFWL54XQ","short_pith_number":"pith:AHCVTNHJ","schema_version":"1.0","canonical_sha256":"01c559b4e9b7ce5796e9fbb25b2fbcbc1d05b6835a1b27425d56d7147f90809a","source":{"kind":"arxiv","id":"2606.03318","version":1},"attestation_state":"computed","paper":{"title":"Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunxiao Liu, Hao Xu, Hongsheng Xin, Kaike Zhang, Ning Miao, Tingfeng Hui, Xuan Yang","submitted_at":"2026-06-02T08:28:37Z","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"},"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":"2606.03318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T08:28:37Z","cross_cats_sorted":[],"title_canon_sha256":"b627a07e74d4f2d6fe2dc39f2e20b360527def0ae9851dad34b08c07f2f5ee58","abstract_canon_sha256":"250bb573fb777ec86332c2912f51bf2e9c4e9e7b85896e96511bc67cbeb2b53b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:54.849728Z","signature_b64":"qEJwMXqrMueJFGoliwRks/KEcEDYNSs+AcugKv4y5EGqV/1l7z60CZ5Oz0G6LYN+3VyHpMWJpxq0g+3h3SpYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01c559b4e9b7ce5796e9fbb25b2fbcbc1d05b6835a1b27425d56d7147f90809a","last_reissued_at":"2026-06-03T01:05:54.849233Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:54.849233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunxiao Liu, Hao Xu, Hongsheng Xin, Kaike Zhang, Ning Miao, Tingfeng Hui, Xuan Yang","submitted_at":"2026-06-02T08:28:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03318","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/2606.03318/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":"2606.03318","created_at":"2026-06-03T01:05:54.849285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03318v1","created_at":"2026-06-03T01:05:54.849285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03318","created_at":"2026-06-03T01:05:54.849285+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHCVTNHJW7HF","created_at":"2026-06-03T01:05:54.849285+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHCVTNHJW7HFPFXJ","created_at":"2026-06-03T01:05:54.849285+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHCVTNHJ","created_at":"2026-06-03T01:05:54.849285+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/AHCVTNHJW7HFPFXJ7OZFWL54XQ","json":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ.json","graph_json":"https://pith.science/api/pith-number/AHCVTNHJW7HFPFXJ7OZFWL54XQ/graph.json","events_json":"https://pith.science/api/pith-number/AHCVTNHJW7HFPFXJ7OZFWL54XQ/events.json","paper":"https://pith.science/paper/AHCVTNHJ"},"agent_actions":{"view_html":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ","download_json":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ.json","view_paper":"https://pith.science/paper/AHCVTNHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03318&json=true","fetch_graph":"https://pith.science/api/pith-number/AHCVTNHJW7HFPFXJ7OZFWL54XQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AHCVTNHJW7HFPFXJ7OZFWL54XQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/action/storage_attestation","attest_author":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/action/author_attestation","sign_citation":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/action/citation_signature","submit_replication":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/action/replication_record"}},"created_at":"2026-06-03T01:05:54.849285+00:00","updated_at":"2026-06-03T01:05:54.849285+00:00"}