{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VIQE5U373KNQRTSSEU2CJ2LJYU","short_pith_number":"pith:VIQE5U37","schema_version":"1.0","canonical_sha256":"aa204ed37fda9b08ce52253424e969c508e1581d745891043b2439213bfa9d4c","source":{"kind":"arxiv","id":"2501.02506","version":4},"attestation_state":"computed","paper":{"title":"ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2025-01-05T11:06:55Z","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"},"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":"2501.02506","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T11:06:55Z","cross_cats_sorted":[],"title_canon_sha256":"f0b00b362e25a493df26eac9ca6f7de532e7fdafa2c47e978d980711e23b4fd3","abstract_canon_sha256":"0fe11098a46f9ce71ed2722663fee0d56d63d65d325f1cba6b928ba9b402374e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:38.203249Z","signature_b64":"fHeIIUGGL7JEUyMNSMDUqyIOPi+SBIIQQP3RBWcGwbn84GOq2hihzQNsVMbDeWDQSvCC6vPtdtDtjKRgjKdfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa204ed37fda9b08ce52253424e969c508e1581d745891043b2439213bfa9d4c","last_reissued_at":"2026-07-05T11:05:38.202786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:38.202786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2025-01-05T11:06:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02506","kind":"arxiv","version":4},"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/2501.02506/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":"2501.02506","created_at":"2026-07-05T11:05:38.202843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02506v4","created_at":"2026-07-05T11:05:38.202843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02506","created_at":"2026-07-05T11:05:38.202843+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIQE5U373KNQ","created_at":"2026-07-05T11:05:38.202843+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIQE5U373KNQRTSS","created_at":"2026-07-05T11:05:38.202843+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIQE5U37","created_at":"2026-07-05T11:05:38.202843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24941","citing_title":"Memory-Induced Tool-Drift in LLM Agents","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU","json":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU.json","graph_json":"https://pith.science/api/pith-number/VIQE5U373KNQRTSSEU2CJ2LJYU/graph.json","events_json":"https://pith.science/api/pith-number/VIQE5U373KNQRTSSEU2CJ2LJYU/events.json","paper":"https://pith.science/paper/VIQE5U37"},"agent_actions":{"view_html":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU","download_json":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU.json","view_paper":"https://pith.science/paper/VIQE5U37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02506&json=true","fetch_graph":"https://pith.science/api/pith-number/VIQE5U373KNQRTSSEU2CJ2LJYU/graph.json","fetch_events":"https://pith.science/api/pith-number/VIQE5U373KNQRTSSEU2CJ2LJYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU/action/storage_attestation","attest_author":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU/action/author_attestation","sign_citation":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU/action/citation_signature","submit_replication":"https://pith.science/pith/VIQE5U373KNQRTSSEU2CJ2LJYU/action/replication_record"}},"created_at":"2026-07-05T11:05:38.202843+00:00","updated_at":"2026-07-05T11:05:38.202843+00:00"}