{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AHCVTNHJW7HFPFXJ7OZFWL54XQ","short_pith_number":"pith:AHCVTNHJ","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"},"canonical_sha256":"01c559b4e9b7ce5796e9fbb25b2fbcbc1d05b6835a1b27425d56d7147f90809a","source":{"kind":"arxiv","id":"2606.03318","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AHCVTNHJW7HFPFXJ7OZFWL54XQ","target":"record","payload":{"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"},"canonical_sha256":"01c559b4e9b7ce5796e9fbb25b2fbcbc1d05b6835a1b27425d56d7147f90809a","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"},"source_kind":"arxiv","source_id":"2606.03318","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oRHzUjXBZTCVTC/N8g0WDj73JuqxNEa0TD+qgMxQsqHP7H2S777P8bPLuQ+0tqKtkTVDJbruh5i8+/5mhbVuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:54:51.963058Z"},"content_sha256":"9b1efdc6790ac26430aaf6b329344fc1a281117abbdf9bae5b54090ed8efe15d","schema_version":"1.0","event_id":"sha256:9b1efdc6790ac26430aaf6b329344fc1a281117abbdf9bae5b54090ed8efe15d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AHCVTNHJW7HFPFXJ7OZFWL54XQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xtHdXYjfFnHXXiiWIwWjEy2TOXA7+4NGyGF92Lrck511HIU9hc+IpF88Hs8LUZYLAZjIyIs5LVnS9eej0qn6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:54:51.963454Z"},"content_sha256":"d397f9d076eaa8fb7cf53bc7d8dcfde7185afc208f3769d1ba711624b22e5f1f","schema_version":"1.0","event_id":"sha256:d397f9d076eaa8fb7cf53bc7d8dcfde7185afc208f3769d1ba711624b22e5f1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/bundle.json","state_url":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T14:54:51Z","links":{"resolver":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ","bundle":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/bundle.json","state":"https://pith.science/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHCVTNHJW7HFPFXJ7OZFWL54XQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5w70WFnOW/YkhRCxH4IyfWFaPMQPdwnUaxd8Bex1JcUwOyHK7/MzcFXXg5lVPQQnt3LHo8rmjkII2qu8IeMsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T14:54:51.965755Z","bundle_sha256":"3ee5c1d83af02b50c2f8a12fcd0ff107aaee4a11146d2c19a223a44cd2f281cf"}}