{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:APVGS7ROOTGAE4YCCRRXDDYOQ7","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":"c91d253a6d35667962bba0c20e181f1489a8fb2e84cfde27bca4b41629f9dc12","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T02:11:01Z","title_canon_sha256":"746c1f729186cfc49427e356db502d9377ee3882241d6dae6808f0939209a1c0"},"schema_version":"1.0","source":{"id":"2606.10315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10315","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10315v1","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10315","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"APVGS7ROOTGA","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"APVGS7ROOTGAE4YC","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"APVGS7RO","created_at":"2026-06-10T01:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:a7b69abd2775737c27da77d2766e8a94ba69f1846be23d0c7df6e97ae06f5705","target":"graph","created_at":"2026-06-10T01:10:11Z","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/2606.10315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-judge is the default instrument for evaluating conversational agents, yet its reliability is almost always reported as agreement with human ratings, not recall of real defects. We study a deployed multi-turn food-and-beverage ordering agent and measure how many genuine quality problems its built-in LLM judge catches, using exhaustive human transcript review as ground truth. Across three batches the judge surfaces well under a quarter of human-confirmed systematic problems -- 2 of 9 patterns (22%) in one batch, and its operational gate flagged zero of 100 rounds in a batch where humans c","authors_text":"Alexander Wang, Sawyer Zhang, Sophie Lei","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T02:11:01Z","title":"Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10315","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:da0fad87d94d6c8396ddc20304e6b88eadfde95ff99ab35b35c445119ccaa18a","target":"record","created_at":"2026-06-10T01:10:11Z","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":"c91d253a6d35667962bba0c20e181f1489a8fb2e84cfde27bca4b41629f9dc12","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T02:11:01Z","title_canon_sha256":"746c1f729186cfc49427e356db502d9377ee3882241d6dae6808f0939209a1c0"},"schema_version":"1.0","source":{"id":"2606.10315","kind":"arxiv","version":1}},"canonical_sha256":"03ea697e2e74cc0273021463718f0e87c8f6da7b1504f074b84d525e1f098aa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03ea697e2e74cc0273021463718f0e87c8f6da7b1504f074b84d525e1f098aa0","first_computed_at":"2026-06-10T01:10:11.381262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:11.381262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IebjIehVcoRbEDg09taSRDOyvU20qBoOf8H01drv3zbJ00DRXVvH/Tac6+5+LVQiEkN2K0JKBGK8eQLsezhaCQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:11.382061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da0fad87d94d6c8396ddc20304e6b88eadfde95ff99ab35b35c445119ccaa18a","sha256:a7b69abd2775737c27da77d2766e8a94ba69f1846be23d0c7df6e97ae06f5705"],"state_sha256":"3c754d77de175278c577c452f7d99f951023549986279f67d7a83fb43b92d662"}