{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MWD3C53ZCD3WRDJWBMT6MJFUIC","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":"88a8ea1c1af76f56b662b9ef1e6d40db468876ec3577bdf94f718d74a2f20238","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T05:55:13Z","title_canon_sha256":"d1a89653e228d46e5b412faaa3ee1fe6eb31ca2c16fa789bdaada4345d9f6015"},"schema_version":"1.0","source":{"id":"2606.11686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11686","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11686v1","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11686","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"MWD3C53ZCD3W","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"MWD3C53ZCD3WRDJW","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"MWD3C53Z","created_at":"2026-06-11T01:10:02Z"}],"graph_snapshots":[{"event_id":"sha256:44e071df32805639bdfbaa674ab241154b9b73ec810b4130ac13634f084b1dbd","target":"graph","created_at":"2026-06-11T01:10:02Z","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/2606.11686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM \"pure\" mode. The pure suite (238 cases across 23 slices; 225 run in 2.39 s, ~10 ms/case) runs in CI on every change against a locked per-slice baseline. We validate by contro","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":"2026-06-10T05:55:13Z","title":"Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11686","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":"sha256:68e9b396c8c23b09cf6b7999cd346e93f57f172831e919f73f8e054c6c7f4d57","target":"record","created_at":"2026-06-11T01:10:02Z","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":"88a8ea1c1af76f56b662b9ef1e6d40db468876ec3577bdf94f718d74a2f20238","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T05:55:13Z","title_canon_sha256":"d1a89653e228d46e5b412faaa3ee1fe6eb31ca2c16fa789bdaada4345d9f6015"},"schema_version":"1.0","source":{"id":"2606.11686","kind":"arxiv","version":1}},"canonical_sha256":"6587b1777910f7688d360b27e624b440b35bdf4467cbfb7708f981e0c1476525","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6587b1777910f7688d360b27e624b440b35bdf4467cbfb7708f981e0c1476525","first_computed_at":"2026-06-11T01:10:02.782158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:02.782158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VncCr13YgV/OQCw8UikfkuczlQGOTtMkb3er8veHOxcC9X4AnGssKevPEnIvU2Dagm3g8qaUsGO2XAh0c/bsBA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:02.782947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68e9b396c8c23b09cf6b7999cd346e93f57f172831e919f73f8e054c6c7f4d57","sha256:44e071df32805639bdfbaa674ab241154b9b73ec810b4130ac13634f084b1dbd"],"state_sha256":"a0d4a0b48f021c1e75c2d8d9cfe4a0d993095f31179601ffaf59902bdf783e09"}