{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RSJG4OBM4CJDYEWM6X6ROGIRKG","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":"3fc69f0a02d1407fd2462ce29e69f05415f556777a84f5bff598f6e2d39d2500","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T14:57:40Z","title_canon_sha256":"27dfabeaefae83fa308d6d7570096d84aeaae9f2ddaaf3ea1364a64dceecee0b"},"schema_version":"1.0","source":{"id":"2403.07714","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07714","created_at":"2026-07-05T10:24:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07714v5","created_at":"2026-07-05T10:24:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07714","created_at":"2026-07-05T10:24:20Z"},{"alias_kind":"pith_short_12","alias_value":"RSJG4OBM4CJD","created_at":"2026-07-05T10:24:20Z"},{"alias_kind":"pith_short_16","alias_value":"RSJG4OBM4CJDYEWM","created_at":"2026-07-05T10:24:20Z"},{"alias_kind":"pith_short_8","alias_value":"RSJG4OBM","created_at":"2026-07-05T10:24:20Z"}],"graph_snapshots":[{"event_id":"sha256:f34cf3028080a36f4ecc3a921326480583f7e59eed4ba1bfcb8b24cbc0f128e9","target":"graph","created_at":"2026-07-05T10:24:20Z","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/2403.07714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to utilise tools necessitates large-scale and stable benchmarks. However, previous works relied on either hand-crafted online tools with limited scale, or large-scale real online APIs suffering from instability of API status. To address this problem, we introduce StableToolBench, a benchmark evolving from ToolBench, proposing a virtual API server and s","authors_text":"Hao Wang, Maosong Sun, Peng Li, Shihao Liang, Sijie Cheng, Yang Liu, Yujia Qin, Zhicheng Guo, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T14:57:40Z","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07714","kind":"arxiv","version":5},"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":"sha256:833b3d909eb094655f0a7793ea07e8da89f0cceb122b20ade2fa192a61c759ef","target":"record","created_at":"2026-07-05T10:24:20Z","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":"3fc69f0a02d1407fd2462ce29e69f05415f556777a84f5bff598f6e2d39d2500","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T14:57:40Z","title_canon_sha256":"27dfabeaefae83fa308d6d7570096d84aeaae9f2ddaaf3ea1364a64dceecee0b"},"schema_version":"1.0","source":{"id":"2403.07714","kind":"arxiv","version":5}},"canonical_sha256":"8c926e382ce0923c12ccf5fd171911519ed5209168b9abd43c666b6fbb2be9f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c926e382ce0923c12ccf5fd171911519ed5209168b9abd43c666b6fbb2be9f4","first_computed_at":"2026-07-05T10:24:20.577074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:20.577074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ERXpY3QB32EM+MdjV9R+aItO4N/X+ZvhG97Pq/U1r7mDXOsEWBPVtO2o82HI9QkADc1Tu2RCwoo6Cxp09AIZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:20.577951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07714","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:833b3d909eb094655f0a7793ea07e8da89f0cceb122b20ade2fa192a61c759ef","sha256:f34cf3028080a36f4ecc3a921326480583f7e59eed4ba1bfcb8b24cbc0f128e9"],"state_sha256":"6e318aced5033e8fda1421b212306bd4bbae3cfe2f489d7ca7b9dca3c8c31655"}