{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KCWBYPZBYJUGCOSTVDPB4JL5FY","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":"f3f5f1af840fb19c3bb7f519b42cddd3c8a6f37053e3da5554e9068a6f884987","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T17:35:20Z","title_canon_sha256":"8869a3877ed28ad6e93e8c1b70dcae80af2c9f172bf3621186c66bb808d6a83f"},"schema_version":"1.0","source":{"id":"2311.04850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04850","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04850v2","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04850","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"KCWBYPZBYJUG","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"KCWBYPZBYJUGCOST","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"KCWBYPZB","created_at":"2026-07-05T07:11:37Z"}],"graph_snapshots":[{"event_id":"sha256:11f9f4db3fce6340e756644136da69ec114ff20a85d86021ca7786e4b584b20c","target":"graph","created_at":"2026-07-05T07:11:37Z","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/2311.04850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly trained on all the data ever produced by humans. Many have raised concerns about the trustworthiness of public benchmarks due to potential contamination in pre-training or fine-tuning datasets. While most data decontamination efforts apply string matching (e.g., n-gram overlap) to remove benchmark data, we show that these methods are insufficient, and simple variations of test data (e.g., paraphrasing, translation) can easily bypass these decontamination measures. Furthermore, we demonstrate that if such variation of test data is not eliminated, a 13B mod","authors_text":"Ion Stoica, Joseph E. Gonzalez, Lianmin Zheng, Shuo Yang, Wei-Lin Chiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T17:35:20Z","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04850","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:ef8139e6edf2a8a8e248b4a9edefc75a68162e266ca91a766736a0582356762a","target":"record","created_at":"2026-07-05T07:11:37Z","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":"f3f5f1af840fb19c3bb7f519b42cddd3c8a6f37053e3da5554e9068a6f884987","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T17:35:20Z","title_canon_sha256":"8869a3877ed28ad6e93e8c1b70dcae80af2c9f172bf3621186c66bb808d6a83f"},"schema_version":"1.0","source":{"id":"2311.04850","kind":"arxiv","version":2}},"canonical_sha256":"50ac1c3f21c268613a53a8de1e257d2e37cefff2950309b4cf9738514b325c73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50ac1c3f21c268613a53a8de1e257d2e37cefff2950309b4cf9738514b325c73","first_computed_at":"2026-07-05T07:11:37.536112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:37.536112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7+67O0SCti73+QAWW3OczlCgDvVhQxnaQkkFkvGdxx0TCcNDibI/w2uqZaqrrtA9N11oq9LqvWlFTKIoTTm5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:37.536644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef8139e6edf2a8a8e248b4a9edefc75a68162e266ca91a766736a0582356762a","sha256:11f9f4db3fce6340e756644136da69ec114ff20a85d86021ca7786e4b584b20c"],"state_sha256":"d2005d31431b387ca58218a0487cba41b0cf1986ce77684b1cdf7da84247b21f"}