{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6OMJZYBFNILPL4FJ2T4ABQGQ2B","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":"60b7cff45ce6e4f006d876ded4e71a03322f327f2f5e653d8ea4d813a4226ad3","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:34:34Z","title_canon_sha256":"294139c20dabd8e5d17c44cf42a31301b8f2daf837a26f8a570b5b747df90900"},"schema_version":"1.0","source":{"id":"2606.25819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25819","created_at":"2026-06-25T01:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25819v1","created_at":"2026-06-25T01:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25819","created_at":"2026-06-25T01:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"6OMJZYBFNILP","created_at":"2026-06-25T01:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"6OMJZYBFNILPL4FJ","created_at":"2026-06-25T01:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"6OMJZYBF","created_at":"2026-06-25T01:18:40Z"}],"graph_snapshots":[{"event_id":"sha256:4b6b470c63a25704693a166c1988ea94be4c98eabb70861bba9a18b307140134","target":"graph","created_at":"2026-06-25T01:18:40Z","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/2606.25819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover complex task settings, they still largely assume clean, stable, and trustworthy tool environments, leaving tool-environment unreliability insufficiently examined. We introduce ToolBench-X, a benchmark for evaluating agents under recoverable reliability hazards. ToolBench-X contains executable multi-step tasks across diverse domains and sequential, parallel, and mixed workflows, each paired with deterministic tools and ","authors_text":"Bo Zhao, Yang Tian, Zhengpeng Shi","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:34:34Z","title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25819","kind":"arxiv","version":1},"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:becbb9166293b64a0460d9f050c39f7ca876d53410cb1c8318f69b28dbbf3506","target":"record","created_at":"2026-06-25T01:18:40Z","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":"60b7cff45ce6e4f006d876ded4e71a03322f327f2f5e653d8ea4d813a4226ad3","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:34:34Z","title_canon_sha256":"294139c20dabd8e5d17c44cf42a31301b8f2daf837a26f8a570b5b747df90900"},"schema_version":"1.0","source":{"id":"2606.25819","kind":"arxiv","version":1}},"canonical_sha256":"f3989ce0256a16f5f0a9d4f800c0d0d05aaf70fcfbe932d11e12452c926678dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3989ce0256a16f5f0a9d4f800c0d0d05aaf70fcfbe932d11e12452c926678dd","first_computed_at":"2026-06-25T01:18:40.329131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:40.329131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E0tDi4tOmd2VzcNhY54jkOmcWCE63wUi9zLVFb/VdVxeNoqIGIR6gaM8cDNn972Nhgwv/ArF7WdwXuWdMoeMCg==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:40.329597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:becbb9166293b64a0460d9f050c39f7ca876d53410cb1c8318f69b28dbbf3506","sha256:4b6b470c63a25704693a166c1988ea94be4c98eabb70861bba9a18b307140134"],"state_sha256":"f82f19db1813f0ecd766a9874f4eec951910f1d750013f9992e79dabb3007b9e"}