{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:75LO3J3KDQSR6FC45AYFQZUXFQ","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":"69996d22e6c0f2b195bc59b9399557bbf77aa411debc6da83043f639d028acb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T09:16:39Z","title_canon_sha256":"3bee58ea9ac08bd9e46a82a5e55e11a710250e3022159903cb42888473960cfc"},"schema_version":"1.0","source":{"id":"2605.21543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21543","created_at":"2026-05-22T00:02:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21543v1","created_at":"2026-05-22T00:02:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21543","created_at":"2026-05-22T00:02:28Z"},{"alias_kind":"pith_short_12","alias_value":"75LO3J3KDQSR","created_at":"2026-05-22T00:02:28Z"},{"alias_kind":"pith_short_16","alias_value":"75LO3J3KDQSR6FC4","created_at":"2026-05-22T00:02:28Z"},{"alias_kind":"pith_short_8","alias_value":"75LO3J3K","created_at":"2026-05-22T00:02:28Z"}],"graph_snapshots":[{"event_id":"sha256:57c34a0f9a9b4a2d2410d663f8d1d9171cc4d9faaef6de329f20665fc8644306","target":"graph","created_at":"2026-05-22T00:02:28Z","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/2605.21543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performance can be inflated and cross-model comparisons become unreliable. A broad line of training-data detection work designs scores to quantify how strongly a model memorizes a given data point, but these score-based methods lack theoretical guarantees. Recent conformal approaches provide provable false-identification control for a single model; however, applying them separately to each model can produce model-specific be","authors_text":"Hao Zeng, Hongxin Wei, Zhenlong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T09:16:39Z","title":"Provable Joint Decontamination for Benchmarking Multiple Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21543","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:eed8592dbd29920e2cd171789e1c5c97ef17f4da6eb1c0e377ffc5a5371f22f7","target":"record","created_at":"2026-05-22T00:02:28Z","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":"69996d22e6c0f2b195bc59b9399557bbf77aa411debc6da83043f639d028acb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T09:16:39Z","title_canon_sha256":"3bee58ea9ac08bd9e46a82a5e55e11a710250e3022159903cb42888473960cfc"},"schema_version":"1.0","source":{"id":"2605.21543","kind":"arxiv","version":1}},"canonical_sha256":"ff56eda76a1c251f145ce8305866972c2947cc381e224b7b33d8e028e633977c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff56eda76a1c251f145ce8305866972c2947cc381e224b7b33d8e028e633977c","first_computed_at":"2026-05-22T00:02:28.054051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T00:02:28.054051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pHkN+6E1bTZc9SJi+GbWCx5Ps3tCSKenCY20LcWSQ9o/PWgcOVHJMeHCm2aMwEjfpQz6OtLzXFZ77t7dVAnFAQ==","signature_status":"signed_v1","signed_at":"2026-05-22T00:02:28.054515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eed8592dbd29920e2cd171789e1c5c97ef17f4da6eb1c0e377ffc5a5371f22f7","sha256:57c34a0f9a9b4a2d2410d663f8d1d9171cc4d9faaef6de329f20665fc8644306"],"state_sha256":"8caa85c4adf101016791a835e13768cb8fa0cf961d0e2f4785448a3b11e7711e"}