{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3KHTVI32RWK3GZR4YZJOTVRGVS","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":"a2bd5b5447d8df2df6be8caec7e00cbc537c68a1fd2c5c2819fad8a1510ee92b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T17:50:09Z","title_canon_sha256":"45e4dd412c4bce0bed06aaa57184a28206f28151340b58a5185941e24cc290fd"},"schema_version":"1.0","source":{"id":"2407.08713","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08713","created_at":"2026-07-05T09:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08713v2","created_at":"2026-07-05T09:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08713","created_at":"2026-07-05T09:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"3KHTVI32RWK3","created_at":"2026-07-05T09:39:07Z"},{"alias_kind":"pith_short_16","alias_value":"3KHTVI32RWK3GZR4","created_at":"2026-07-05T09:39:07Z"},{"alias_kind":"pith_short_8","alias_value":"3KHTVI32","created_at":"2026-07-05T09:39:07Z"}],"graph_snapshots":[{"event_id":"sha256:e4c206f8ecb1184d8ca41122146a9e7ffb462f26897144c96969954cf94d4e66","target":"graph","created_at":"2026-07-05T09:39:07Z","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/2407.08713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant focus has been placed on integrating large language models (LLMs) with various tools in developing general-purpose agents. This poses a challenge to LLMs' tool-use capabilities. However, there are evident gaps between existing tool-use evaluations and real-world scenarios. Current evaluations often use AI-generated queries, single-step tasks, dummy tools, and text-only interactions, failing to reveal the agents' real-world problem-solving abilities effectively. To address this, we propose GTA, a benchmark for General Tool Agents, featuring three main aspects: (i) Real user queries:","authors_text":"Cailian Chen, Jize Wang, Kai Chen, Songyang Zhang, Xinyi Le, Yining Li, Zerun Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T17:50:09Z","title":"GTA: A Benchmark for General Tool Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08713","kind":"arxiv","version":2},"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:dbaf867fd5c96741b8d3d61f2dec0c72cefde126c8002c5ae292a52bb49b59cb","target":"record","created_at":"2026-07-05T09:39:07Z","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":"a2bd5b5447d8df2df6be8caec7e00cbc537c68a1fd2c5c2819fad8a1510ee92b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T17:50:09Z","title_canon_sha256":"45e4dd412c4bce0bed06aaa57184a28206f28151340b58a5185941e24cc290fd"},"schema_version":"1.0","source":{"id":"2407.08713","kind":"arxiv","version":2}},"canonical_sha256":"da8f3aa37a8d95b3663cc652e9d626ac8f2cee03f8354865d81ff55d940488dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da8f3aa37a8d95b3663cc652e9d626ac8f2cee03f8354865d81ff55d940488dc","first_computed_at":"2026-07-05T09:39:07.839198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:07.839198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f2fFuoCA3Ax3vP8iJmqmStxZWKuDnzTvdNhNORX3rTvMs1jOlrwQv0+zTvDtXbn1SDBy/lzS02xq4QeEHQEPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:07.839690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08713","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbaf867fd5c96741b8d3d61f2dec0c72cefde126c8002c5ae292a52bb49b59cb","sha256:e4c206f8ecb1184d8ca41122146a9e7ffb462f26897144c96969954cf94d4e66"],"state_sha256":"cc9e685cdce81c2bf18908684a4d460d175938cb45d52934a1cf4a889e1d619e"}