{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VIQE5U373KNQRTSSEU2CJ2LJYU","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":"0fe11098a46f9ce71ed2722663fee0d56d63d65d325f1cba6b928ba9b402374e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T11:06:55Z","title_canon_sha256":"f0b00b362e25a493df26eac9ca6f7de532e7fdafa2c47e978d980711e23b4fd3"},"schema_version":"1.0","source":{"id":"2501.02506","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02506","created_at":"2026-07-05T11:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02506v4","created_at":"2026-07-05T11:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02506","created_at":"2026-07-05T11:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"VIQE5U373KNQ","created_at":"2026-07-05T11:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"VIQE5U373KNQRTSS","created_at":"2026-07-05T11:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"VIQE5U37","created_at":"2026-07-05T11:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:5daae98cedd78ad00bbdf450b2fa87af4a508e3f3c26cddb0e82da9de04c08cd","target":"graph","created_at":"2026-07-05T11:05:38Z","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/2501.02506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models (LLMs). However, progress has been hindered by a lack of reliable evaluation datasets. To address this, we present ToolHop, a dataset comprising 995 user queries and 3,912 associated tools, specifically designed for rigorous evaluation of multi-hop tool use. ToolHop ensures diverse queries, meaningful interdependencies, locally executable tools, detailed feedback, and verifiable answers through a novel query-driven data construction appro","authors_text":"Jiecao Chen, Junjie Ye, Qi Zhang, Sining Zhu, Siyu Yuan, Tao Gui, Weijian Lin, Xuanjing Huang, Xuesong Yao, Yufei Xu, Zaiyuan Wang, Zehui Chen, Zhengyin Du, Zhiheng Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T11:06:55Z","title":"ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02506","kind":"arxiv","version":4},"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":"sha256:7e2967da81b68292a673df56d088cdce3360bd3fe1a15d133698110f4c83656c","target":"record","created_at":"2026-07-05T11:05:38Z","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":"0fe11098a46f9ce71ed2722663fee0d56d63d65d325f1cba6b928ba9b402374e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T11:06:55Z","title_canon_sha256":"f0b00b362e25a493df26eac9ca6f7de532e7fdafa2c47e978d980711e23b4fd3"},"schema_version":"1.0","source":{"id":"2501.02506","kind":"arxiv","version":4}},"canonical_sha256":"aa204ed37fda9b08ce52253424e969c508e1581d745891043b2439213bfa9d4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa204ed37fda9b08ce52253424e969c508e1581d745891043b2439213bfa9d4c","first_computed_at":"2026-07-05T11:05:38.202786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:38.202786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fHeIIUGGL7JEUyMNSMDUqyIOPi+SBIIQQP3RBWcGwbn84GOq2hihzQNsVMbDeWDQSvCC6vPtdtDtjKRgjKdfAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:38.203249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02506","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e2967da81b68292a673df56d088cdce3360bd3fe1a15d133698110f4c83656c","sha256:5daae98cedd78ad00bbdf450b2fa87af4a508e3f3c26cddb0e82da9de04c08cd"],"state_sha256":"c4d414620be76656062cb2de33040f593d708f97a5a0c1c101f53a79370e2e03"}