{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KIN7B4ATSQNOJWEPT4HK35ICM6","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":"ae4b764ea964f81bdbb2639735f270c6491cb7c98cbab629b0627fb335ba5a7c","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-08T01:37:45Z","title_canon_sha256":"8325c3270969d5258186ae5386313663b39cdb5ad8f39814f91e8249b4b91842"},"schema_version":"1.0","source":{"id":"2603.10044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10044","created_at":"2026-06-04T02:07:45Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10044v2","created_at":"2026-06-04T02:07:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10044","created_at":"2026-06-04T02:07:45Z"},{"alias_kind":"pith_short_12","alias_value":"KIN7B4ATSQNO","created_at":"2026-06-04T02:07:45Z"},{"alias_kind":"pith_short_16","alias_value":"KIN7B4ATSQNOJWEP","created_at":"2026-06-04T02:07:45Z"},{"alias_kind":"pith_short_8","alias_value":"KIN7B4AT","created_at":"2026-06-04T02:07:45Z"}],"graph_snapshots":[{"event_id":"sha256:107f6a829418eb3233ffb9684e30b735cb809763f5cafd142cb97fd77f3b87a3","target":"graph","created_at":"2026-06-04T02:07:45Z","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/2603.10044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A safety score earned on a benchmark need not predict how the same model behaves once it is wrapped in an agentic scaffold the benchmark never tested. We ran six frontier models through four deployment configurations (direct API, ReAct, multi-agent critic, map-reduce delegation): N = 62,808 blinded, pre-registered, equivalence-tested evaluations across four safety benchmarks (BBQ, TruthfulQA, XSTest/OR-Bench, sycophancy), plus three supporting analyses.\n  ReAct and multi-agent scaffolds stay within a pre-registered +/-2 pp equivalence margin; map-reduce delegation degrades measured safety (NNH","authors_text":"David Gringras","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-08T01:37:45Z","title":"Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10044","kind":"arxiv","version":2},"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:eca7c3ad7983855734c09007dfc7aab82b06ddfcc157cf7318bfca99db4644ee","target":"record","created_at":"2026-06-04T02:07:45Z","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":"ae4b764ea964f81bdbb2639735f270c6491cb7c98cbab629b0627fb335ba5a7c","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-08T01:37:45Z","title_canon_sha256":"8325c3270969d5258186ae5386313663b39cdb5ad8f39814f91e8249b4b91842"},"schema_version":"1.0","source":{"id":"2603.10044","kind":"arxiv","version":2}},"canonical_sha256":"521bf0f013941ae4d88f9f0eadf502678bf11b90cea406cf1661b4d94c8df7e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"521bf0f013941ae4d88f9f0eadf502678bf11b90cea406cf1661b4d94c8df7e7","first_computed_at":"2026-06-04T02:07:45.490896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T02:07:45.490896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GD4rUUUy7+jKu4hw7Xo7+t93UobnD6GQpdbNpyNh6MACRHZAvNFo/5JhyCzwTHE9H3S4Dw0VfATYGAZZmqOmAA==","signature_status":"signed_v1","signed_at":"2026-06-04T02:07:45.491671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eca7c3ad7983855734c09007dfc7aab82b06ddfcc157cf7318bfca99db4644ee","sha256:107f6a829418eb3233ffb9684e30b735cb809763f5cafd142cb97fd77f3b87a3"],"state_sha256":"6bd928123e92443745b53ad632542b86ab82f4d80562b1c8405bef991e5c0f6c"}