{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NSP33S557MWOYM7EPCUVQ7FIR7","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":"e3448e3b1681d0de34a617ad25bfc13eec75144cc01c2c264d02bea38cf6287b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-13T05:14:12Z","title_canon_sha256":"f75246f030b17af76b7e5f1c838a04bbaf3c10e325518f6ea7531469d1701383"},"schema_version":"1.0","source":{"id":"2607.11098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11098","created_at":"2026-07-14T01:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11098v1","created_at":"2026-07-14T01:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11098","created_at":"2026-07-14T01:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"NSP33S557MWO","created_at":"2026-07-14T01:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"NSP33S557MWOYM7E","created_at":"2026-07-14T01:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"NSP33S55","created_at":"2026-07-14T01:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:db673ce539c02bcc0ea75cfd3a3698c3a2f686fa7dcec2c9d86a88e9ff17abc9","target":"graph","created_at":"2026-07-14T01:22:16Z","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/2607.11098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description poisoned in deployment, the developer needs a controlled way to reproduce the failure, test a fix, and confirm the fix worked before deployment. We present AgentCheck, an open-source web workbench that turns an MCP server into an intervention surface. AgentCheck runs an agent against its real tools and records every tool response, then re-runs the agent with the response perturbed by a fault (12 types) injector. Matching tool calls are replayed from cach","authors_text":"Aritra Mazumder, Nusrat Jahan Lia","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-13T05:14:12Z","title":"AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11098","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":"sha256:2fa6505bc059351c695684d19098caf2a898268503ebdf1e73877eedb64c09fe","target":"record","created_at":"2026-07-14T01:22:16Z","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":"e3448e3b1681d0de34a617ad25bfc13eec75144cc01c2c264d02bea38cf6287b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-13T05:14:12Z","title_canon_sha256":"f75246f030b17af76b7e5f1c838a04bbaf3c10e325518f6ea7531469d1701383"},"schema_version":"1.0","source":{"id":"2607.11098","kind":"arxiv","version":1}},"canonical_sha256":"6c9fbdcbbdfb2cec33e478a9587ca88ffe8e1114177fe81c09c7e15b5148d600","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c9fbdcbbdfb2cec33e478a9587ca88ffe8e1114177fe81c09c7e15b5148d600","first_computed_at":"2026-07-14T01:22:16.260493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:16.260493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TrKczaxD4FokiW4YptvGfUXKdmKLHUsGWPBT6lzDPx2gPFDcO0ESPnFcRPKxc7FAJTDHLcqm73xyCixckRtlCQ==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:16.261391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fa6505bc059351c695684d19098caf2a898268503ebdf1e73877eedb64c09fe","sha256:db673ce539c02bcc0ea75cfd3a3698c3a2f686fa7dcec2c9d86a88e9ff17abc9"],"state_sha256":"3d8360cb5804d30f769b13c948a39fe7a4ed7f7d1d209dc9c18fe07519fd968c"}