{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FKDMI3QL7IL2RRHL6PF6V635IK","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":"a4056fd9bd3939be6462a1ea31cc57e0bf91152a9dd7e991faa04f61136db3bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T16:03:30Z","title_canon_sha256":"ae0c461e4733af3e490e00e6f7e533b80a0ca71ca221946a262a59a99735fb72"},"schema_version":"1.0","source":{"id":"2406.20015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20015","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20015v2","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20015","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"FKDMI3QL7IL2","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"FKDMI3QL7IL2RRHL","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"FKDMI3QL","created_at":"2026-07-05T09:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:caf0f23672d4397707ddc70a070d47c003bff8286425d36faf59305c2fed06a4","target":"graph","created_at":"2026-07-05T09:15:34Z","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/2406.20015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios ba","authors_text":"Cheng Yang, Chufan Shi, Hanwen Wan, Hayato Yamana, Jing Chen, Junjie Wang, Tetsuya Sakai, Tian Feng, Xinyu Zhu, Yaxin Liu, Yujiu Yang, Yuxiang Zhang, Zihao Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T16:03:30Z","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20015","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:f7c2827e605c36495684881d47ced714abc1b0c84579c63494ccee362d7a49d1","target":"record","created_at":"2026-07-05T09:15:34Z","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":"a4056fd9bd3939be6462a1ea31cc57e0bf91152a9dd7e991faa04f61136db3bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T16:03:30Z","title_canon_sha256":"ae0c461e4733af3e490e00e6f7e533b80a0ca71ca221946a262a59a99735fb72"},"schema_version":"1.0","source":{"id":"2406.20015","kind":"arxiv","version":2}},"canonical_sha256":"2a86c46e0bfa17a8c4ebf3cbeafb7d428b6bcee441804a83256b723d86dafb04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a86c46e0bfa17a8c4ebf3cbeafb7d428b6bcee441804a83256b723d86dafb04","first_computed_at":"2026-07-05T09:15:34.504686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:34.504686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ilFWQgvYEWqfuthXiMQ4eVmi08CYMqVzJN1xUrGSvhhqPtRkVYQOqdcSyV7s7CCzjs2D/JKOVtRW5AgWFkCQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:34.505254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.20015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7c2827e605c36495684881d47ced714abc1b0c84579c63494ccee362d7a49d1","sha256:caf0f23672d4397707ddc70a070d47c003bff8286425d36faf59305c2fed06a4"],"state_sha256":"6929ade594d16d1e75067cc6f570090ab548109b067e28aebf18996ad08b5bb5"}