{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZM3OD6UNANXV63OP35FJTJHVJH","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":"a2826931c24433dca81b023f1e6498037a9fd4178ce5da67fe7c33483170f200","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T08:21:22Z","title_canon_sha256":"3b442cade36879c90c8a31349fcc23a9488bfb27a577c7cafe7d87d8f3f57631"},"schema_version":"1.0","source":{"id":"2606.03305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03305","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03305v1","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03305","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZM3OD6UNANXV","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZM3OD6UNANXV63OP","created_at":"2026-06-03T01:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZM3OD6UN","created_at":"2026-06-03T01:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:1bc4b8502cd350aefb007621d0ded8d4eca3ab2dd05d39ccbf24378bb420b5d2","target":"graph","created_at":"2026-06-03T01:05:54Z","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/2606.03305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for detecting training-data membership exist, but have been validated almost exclusively in controlled academic regimes: large, homogeneous pre-training corpora and transparent, single-stage training pipelines. Whether these methods remain reliable in realistic auditing scenarios remains unclear. We identify two under-studied failure modes: distribution shift, which arises when suspect and validation sets violate the IID assumption, and scale constra","authors_text":"Jan Dubi\\'nski, Sebastian Cygert, Wojciech Zarzecki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T08:21:22Z","title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03305","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":"sha256:0e92c3bd2e13beea3822ed1fc882047d30212dc289d6e20739ff5689a9268221","target":"record","created_at":"2026-06-03T01:05:54Z","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":"a2826931c24433dca81b023f1e6498037a9fd4178ce5da67fe7c33483170f200","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T08:21:22Z","title_canon_sha256":"3b442cade36879c90c8a31349fcc23a9488bfb27a577c7cafe7d87d8f3f57631"},"schema_version":"1.0","source":{"id":"2606.03305","kind":"arxiv","version":1}},"canonical_sha256":"cb36e1fa8d036f5f6dcfdf4a99a4f549d8ce164cfbccbbed5d217c7103c20726","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb36e1fa8d036f5f6dcfdf4a99a4f549d8ce164cfbccbbed5d217c7103c20726","first_computed_at":"2026-06-03T01:05:54.536895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:54.536895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PSLsimvXOELpQAWYrV3DY4Agzon/LnBSzP1xP4cDl58FjYu46O++EaMC8xSV2qO+bbeFUmvpFseGIqAgqyrzCQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:54.537290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e92c3bd2e13beea3822ed1fc882047d30212dc289d6e20739ff5689a9268221","sha256:1bc4b8502cd350aefb007621d0ded8d4eca3ab2dd05d39ccbf24378bb420b5d2"],"state_sha256":"f97327fec5e702239274d3babce1ff0106173c56f518181ebc502b5affd622a2"}