{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6HQECEZMIFBJU6Y2EQ3MKG3MSO","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":"706a14dce8b2b32452292fcd88c8f87d5ad8ec0bb20d9db097f52351afee7e05","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-01T22:28:31Z","title_canon_sha256":"2ddfe9a098eb9ee22434eb69ec59434dc7fd6e5eff670ac3a484e92729e12791"},"schema_version":"1.0","source":{"id":"2608.02665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02665","created_at":"2026-08-05T00:38:30Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02665v1","created_at":"2026-08-05T00:38:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02665","created_at":"2026-08-05T00:38:30Z"},{"alias_kind":"pith_short_12","alias_value":"6HQECEZMIFBJ","created_at":"2026-08-05T00:38:30Z"},{"alias_kind":"pith_short_16","alias_value":"6HQECEZMIFBJU6Y2","created_at":"2026-08-05T00:38:30Z"},{"alias_kind":"pith_short_8","alias_value":"6HQECEZM","created_at":"2026-08-05T00:38:30Z"}],"graph_snapshots":[{"event_id":"sha256:162626223cad7355fe20effec2838b11d1c6a8eff000c20797fcc0ce20eefe29","target":"graph","created_at":"2026-08-05T00:38:30Z","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/2608.02665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is faithful: when an item's intent is held fixed and only its meaning-preserving surface form varies, does the canonical-form score estimate model behavior well, and how much of any variation is decoding/judge noise rather than signal? We instantiate this in safety, a high-stakes setting with no gold label to average toward. To avoid prior confounds, we pre-author the reformulations (refusal-free, mostly non-LLM: machine back-translation and a Matrix","authors_text":"Jiaxi Wen, Junwei Yao, Lai Yun Choi, Wenbo Ye, Yongxi Zhou, Yuanzhe Liu, Zihan Dong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-01T22:28:31Z","title":"Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02665","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:fe0d47b9565698e58bd844b5312e9425712b86cc8718e0ea567bc2da9e3c6c16","target":"record","created_at":"2026-08-05T00:38:30Z","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":"706a14dce8b2b32452292fcd88c8f87d5ad8ec0bb20d9db097f52351afee7e05","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-01T22:28:31Z","title_canon_sha256":"2ddfe9a098eb9ee22434eb69ec59434dc7fd6e5eff670ac3a484e92729e12791"},"schema_version":"1.0","source":{"id":"2608.02665","kind":"arxiv","version":1}},"canonical_sha256":"f1e041132c41429a7b1a2436c51b6c93ae1e603cfc2cde11598a9904db66afa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1e041132c41429a7b1a2436c51b6c93ae1e603cfc2cde11598a9904db66afa6","first_computed_at":"2026-08-05T00:38:30.158075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:38:30.158075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qgk+iz7CzC7KMyLL6zYEAjs7JrID5jSiLMnJWhrZQKf7ZS5Te3BJxFvxxfXEGq4QLFy0rVOBBJ8WjTtlg2XZAQ==","signature_status":"signed_v1","signed_at":"2026-08-05T00:38:30.160549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe0d47b9565698e58bd844b5312e9425712b86cc8718e0ea567bc2da9e3c6c16","sha256:162626223cad7355fe20effec2838b11d1c6a8eff000c20797fcc0ce20eefe29"],"state_sha256":"fe2c426cd047f22a31e55d4f6c7b19986a1109a57c9bd7d7bb3c209d135b0765"}