{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MWD3C53ZCD3WRDJWBMT6MJFUIC","short_pith_number":"pith:MWD3C53Z","schema_version":"1.0","canonical_sha256":"6587b1777910f7688d360b27e624b440b35bdf4467cbfb7708f981e0c1476525","source":{"kind":"arxiv","id":"2606.11686","version":1},"attestation_state":"computed","paper":{"title":"Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Wang, Sawyer Zhang, Sophie Lei","submitted_at":"2026-06-10T05:55:13Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.11686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T05:55:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d1a89653e228d46e5b412faaa3ee1fe6eb31ca2c16fa789bdaada4345d9f6015","abstract_canon_sha256":"88a8ea1c1af76f56b662b9ef1e6d40db468876ec3577bdf94f718d74a2f20238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:02.782947Z","signature_b64":"VncCr13YgV/OQCw8UikfkuczlQGOTtMkb3er8veHOxcC9X4AnGssKevPEnIvU2Dagm3g8qaUsGO2XAh0c/bsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6587b1777910f7688d360b27e624b440b35bdf4467cbfb7708f981e0c1476525","last_reissued_at":"2026-06-11T01:10:02.782158Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:02.782158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Wang, Sawyer Zhang, Sophie Lei","submitted_at":"2026-06-10T05:55:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11686","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11686/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.11686","created_at":"2026-06-11T01:10:02.782281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11686v1","created_at":"2026-06-11T01:10:02.782281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11686","created_at":"2026-06-11T01:10:02.782281+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWD3C53ZCD3W","created_at":"2026-06-11T01:10:02.782281+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWD3C53ZCD3WRDJW","created_at":"2026-06-11T01:10:02.782281+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWD3C53Z","created_at":"2026-06-11T01:10:02.782281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC","json":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC.json","graph_json":"https://pith.science/api/pith-number/MWD3C53ZCD3WRDJWBMT6MJFUIC/graph.json","events_json":"https://pith.science/api/pith-number/MWD3C53ZCD3WRDJWBMT6MJFUIC/events.json","paper":"https://pith.science/paper/MWD3C53Z"},"agent_actions":{"view_html":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC","download_json":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC.json","view_paper":"https://pith.science/paper/MWD3C53Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11686&json=true","fetch_graph":"https://pith.science/api/pith-number/MWD3C53ZCD3WRDJWBMT6MJFUIC/graph.json","fetch_events":"https://pith.science/api/pith-number/MWD3C53ZCD3WRDJWBMT6MJFUIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC/action/storage_attestation","attest_author":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC/action/author_attestation","sign_citation":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC/action/citation_signature","submit_replication":"https://pith.science/pith/MWD3C53ZCD3WRDJWBMT6MJFUIC/action/replication_record"}},"created_at":"2026-06-11T01:10:02.782281+00:00","updated_at":"2026-06-11T01:10:02.782281+00:00"}