{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CH7J2YGBK3EYJDIWWBQYJ2ZTCB","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":"391be5c0346383e3f8900d83a301da3e33987a8ffce9a7cfb11c0e2393ff01f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T17:02:06Z","title_canon_sha256":"b825ba9fc05fdb847381138e2a12ed284250d2e855a12f7023a8958bccae65bd"},"schema_version":"1.0","source":{"id":"2312.14033","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14033","created_at":"2026-07-05T07:33:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14033v3","created_at":"2026-07-05T07:33:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14033","created_at":"2026-07-05T07:33:24Z"},{"alias_kind":"pith_short_12","alias_value":"CH7J2YGBK3EY","created_at":"2026-07-05T07:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"CH7J2YGBK3EYJDIW","created_at":"2026-07-05T07:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"CH7J2YGB","created_at":"2026-07-05T07:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:4f418767b62e67c729b6edeb9e58f57837cd222e199767837aee2b50c637854a","target":"graph","created_at":"2026-07-05T07:33:24Z","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/2312.14033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLM) have achieved remarkable performance on various NLP tasks and are augmented by tools for broader applications. Yet, how to evaluate and analyze the tool-utilization capability of LLMs is still under-explored. In contrast to previous works that evaluate models holistically, we comprehensively decompose the tool utilization into multiple sub-processes, including instruction following, planning, reasoning, retrieval, understanding, and review. Based on that, we further introduce T-Eval to evaluate the tool utilization capability step by step. T-Eval disentangles the to","authors_text":"Dahua Lin, Feng Zhao, Jiangning Liu, Jingming Zhuo, Kai Chen, Kuikun Liu, Miao Zheng, Songyang Zhang, Weihua Du, Wenwei Zhang, Zehui Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T17:02:06Z","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14033","kind":"arxiv","version":3},"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:dac54bc1f8ce73f013145b7dbe6bfee870783080867319e44ade2bcfd966c6cc","target":"record","created_at":"2026-07-05T07:33:24Z","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":"391be5c0346383e3f8900d83a301da3e33987a8ffce9a7cfb11c0e2393ff01f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T17:02:06Z","title_canon_sha256":"b825ba9fc05fdb847381138e2a12ed284250d2e855a12f7023a8958bccae65bd"},"schema_version":"1.0","source":{"id":"2312.14033","kind":"arxiv","version":3}},"canonical_sha256":"11fe9d60c156c9848d16b06184eb33107bd37d06c75b20c307bf0e178fb4725c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11fe9d60c156c9848d16b06184eb33107bd37d06c75b20c307bf0e178fb4725c","first_computed_at":"2026-07-05T07:33:24.716683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:24.716683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GSUduK936roZQ4bVSXduu97si2zUNNu8cu+jo7G/C4hP0GZh6C3po92cVrGukwSiHIXkPfu4nxhysTKUaDSjAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:24.717177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14033","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dac54bc1f8ce73f013145b7dbe6bfee870783080867319e44ade2bcfd966c6cc","sha256:4f418767b62e67c729b6edeb9e58f57837cd222e199767837aee2b50c637854a"],"state_sha256":"41777bfbf837620d1a0029af69588e2af0f9ca6643810f4885c29be6370e38c2"}