{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y3W2ULBWBQP5US3BVJO54KWP6O","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8eeef6eebdcc598930995321bc58c44b9cf41aaf0a51b69ca48d4eac5eb032b4","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T05:30:07Z","title_canon_sha256":"7272eee5b8a7b50fac32b884aadc35b6bff90c8cc92eed85418d92b890e1cebf"},"schema_version":"1.0","source":{"id":"2607.02586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02586","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02586v1","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02586","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y3W2ULBWBQP5","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y3W2ULBWBQP5US3B","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y3W2ULBW","created_at":"2026-07-07T00:16:01Z"}],"graph_snapshots":[{"event_id":"sha256:532d4026f6dcde563ea7e684c53b7a5066fc3957c355adf01c85aaf286f0c871","target":"graph","created_at":"2026-07-07T00:16:01Z","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/2607.02586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Governance frameworks ask AI providers and auditors for documented evaluation evidence, and perturbation-based construct-validity audits are a common form of that evidence. We argue the audits are themselves fragile: their conclusions can be silently manufactured by implementation details that readers cannot see in the reported numbers. We name five classes of pipeline failure and demonstrate each in a self-audit over safety benchmarks and open-weight instruction-tuned models. Under a unified six-point due-diligence gate, every cell lands in a non-confirmatory bucket, and no cell reaches confi","authors_text":"Yanhang Li, Zexin Zhuang, Zhichao Fan","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T05:30:07Z","title":"Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02586","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":"sha256:92b29b4f6f632525cfb551e51e56491ea4bcd21542428211fcf8b71e88a5241e","target":"record","created_at":"2026-07-07T00:16:01Z","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":"8eeef6eebdcc598930995321bc58c44b9cf41aaf0a51b69ca48d4eac5eb032b4","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T05:30:07Z","title_canon_sha256":"7272eee5b8a7b50fac32b884aadc35b6bff90c8cc92eed85418d92b890e1cebf"},"schema_version":"1.0","source":{"id":"2607.02586","kind":"arxiv","version":1}},"canonical_sha256":"c6edaa2c360c1fda4b61aa5dde2acff3a9681bb4ccd71b69c8eb1c15b59dc9cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6edaa2c360c1fda4b61aa5dde2acff3a9681bb4ccd71b69c8eb1c15b59dc9cf","first_computed_at":"2026-07-07T00:16:01.704674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:16:01.704674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kg+sPu24ev17prW157f3fdph1Nu/NP1LNZLkpuNLaJVTLswNNHhhahKkiFF540zkVs+R6ytryPlarMxihaOtDg==","signature_status":"signed_v1","signed_at":"2026-07-07T00:16:01.705373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92b29b4f6f632525cfb551e51e56491ea4bcd21542428211fcf8b71e88a5241e","sha256:532d4026f6dcde563ea7e684c53b7a5066fc3957c355adf01c85aaf286f0c871","sha256:d12ef0613e76d0b2acc6032bee7a453a4d3fd30e862890aad3d6a73acd26b157"],"state_sha256":"01e70d4007eb3fd89e5db417d18c69ff2d5236d6fcdd533681efc7ce9789ad0d"}