{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:D2GJM3LRAWDHDQB2TOBRHTDPA2","short_pith_number":"pith:D2GJM3LR","canonical_record":{"source":{"id":"2311.09154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:50:30Z","cross_cats_sorted":[],"title_canon_sha256":"092aae94201ef1905b6570fa5f7b5d75d03461cf1c6093dd6d7841b5785f69c6","abstract_canon_sha256":"06ca8f7040d01fd0ce8106418f84f8627d304eff9d53233cbefb31b063242b3c"},"schema_version":"1.0"},"canonical_sha256":"1e8c966d71058671c03a9b8313cc6f06ae118c77f7759cde09f88182e192d31c","source":{"kind":"arxiv","id":"2311.09154","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09154","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09154v3","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09154","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"D2GJM3LRAWDH","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"D2GJM3LRAWDHDQB2","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"D2GJM3LR","created_at":"2026-07-05T08:26:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:D2GJM3LRAWDHDQB2TOBRHTDPA2","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:50:30Z","cross_cats_sorted":[],"title_canon_sha256":"092aae94201ef1905b6570fa5f7b5d75d03461cf1c6093dd6d7841b5785f69c6","abstract_canon_sha256":"06ca8f7040d01fd0ce8106418f84f8627d304eff9d53233cbefb31b063242b3c"},"schema_version":"1.0"},"canonical_sha256":"1e8c966d71058671c03a9b8313cc6f06ae118c77f7759cde09f88182e192d31c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:15.630927Z","signature_b64":"5HkpO0OBiNAureNDhrnKaPSN7yxVo2k2WW35h+TV/hEuhQyWi03CXjNH3z2Z6qFxe/VooIypoScQjYiNKqf3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e8c966d71058671c03a9b8313cc6f06ae118c77f7759cde09f88182e192d31c","last_reissued_at":"2026-07-05T08:26:15.630497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:15.630497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09154","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSd15cVpqvsJTcJg6tU6SVT9euMuueuwCqsJY3Dhh831XP3yj9SaI0HpRZi9XXFnV5SVnA2vzppN/gFJTLQmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T00:15:42.300083Z"},"content_sha256":"85c16019d689d0731daee0c3892eddee8e0be03448062f6899382fd2e802e130","schema_version":"1.0","event_id":"sha256:85c16019d689d0731daee0c3892eddee8e0be03448062f6899382fd2e802e130"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:D2GJM3LRAWDHDQB2TOBRHTDPA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanxu Hu, Hongkun Hao, Hongyuan Lu, Rui Wang, Wenhong Zhu, Yiran Wei, Yumeng Zhang, Yunze Song, Zhiwei He","submitted_at":"2023-11-15T17:50:30Z","abstract_excerpt":"We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessing the capabilities of these LLMs has become a challenging and critical issue due to potential data contamination, and it wastes dozens of time and effort for researchers and engineers to download and try those contaminated models. To save our precious time, we propose a novel and useful method, Clean-Eval, which mitigates the issue of data contamination and evaluates the LLMs in a cleaner manner. Clean-Eval employs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09154","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.09154/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wF7CXBqK9eQZon0IMRxM2bEP0YrIbYE1xpYAgLZjHRLWeInR4NXC+UEvSEJYLoW/bdkNFBbHETQeObjaueYmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T00:15:42.300476Z"},"content_sha256":"bb3278423f1696a400840b8adb38a6004498e5ec7b303d9946fd7e6e65c71458","schema_version":"1.0","event_id":"sha256:bb3278423f1696a400840b8adb38a6004498e5ec7b303d9946fd7e6e65c71458"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2/bundle.json","state_url":"https://pith.science/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-12T00:15:42Z","links":{"resolver":"https://pith.science/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2","bundle":"https://pith.science/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2/bundle.json","state":"https://pith.science/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D2GJM3LRAWDHDQB2TOBRHTDPA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D2GJM3LRAWDHDQB2TOBRHTDPA2","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":"06ca8f7040d01fd0ce8106418f84f8627d304eff9d53233cbefb31b063242b3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:50:30Z","title_canon_sha256":"092aae94201ef1905b6570fa5f7b5d75d03461cf1c6093dd6d7841b5785f69c6"},"schema_version":"1.0","source":{"id":"2311.09154","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09154","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09154v3","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09154","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"D2GJM3LRAWDH","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"D2GJM3LRAWDHDQB2","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"D2GJM3LR","created_at":"2026-07-05T08:26:15Z"}],"graph_snapshots":[{"event_id":"sha256:bb3278423f1696a400840b8adb38a6004498e5ec7b303d9946fd7e6e65c71458","target":"graph","created_at":"2026-07-05T08:26:15Z","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/2311.09154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessing the capabilities of these LLMs has become a challenging and critical issue due to potential data contamination, and it wastes dozens of time and effort for researchers and engineers to download and try those contaminated models. To save our precious time, we propose a novel and useful method, Clean-Eval, which mitigates the issue of data contamination and evaluates the LLMs in a cleaner manner. Clean-Eval employs ","authors_text":"Hanxu Hu, Hongkun Hao, Hongyuan Lu, Rui Wang, Wenhong Zhu, Yiran Wei, Yumeng Zhang, Yunze Song, Zhiwei He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:50:30Z","title":"CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09154","kind":"arxiv","version":3},"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":"sha256:85c16019d689d0731daee0c3892eddee8e0be03448062f6899382fd2e802e130","target":"record","created_at":"2026-07-05T08:26:15Z","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":"06ca8f7040d01fd0ce8106418f84f8627d304eff9d53233cbefb31b063242b3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:50:30Z","title_canon_sha256":"092aae94201ef1905b6570fa5f7b5d75d03461cf1c6093dd6d7841b5785f69c6"},"schema_version":"1.0","source":{"id":"2311.09154","kind":"arxiv","version":3}},"canonical_sha256":"1e8c966d71058671c03a9b8313cc6f06ae118c77f7759cde09f88182e192d31c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e8c966d71058671c03a9b8313cc6f06ae118c77f7759cde09f88182e192d31c","first_computed_at":"2026-07-05T08:26:15.630497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:15.630497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5HkpO0OBiNAureNDhrnKaPSN7yxVo2k2WW35h+TV/hEuhQyWi03CXjNH3z2Z6qFxe/VooIypoScQjYiNKqf3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:15.630927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09154","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85c16019d689d0731daee0c3892eddee8e0be03448062f6899382fd2e802e130","sha256:bb3278423f1696a400840b8adb38a6004498e5ec7b303d9946fd7e6e65c71458"],"state_sha256":"360711cbdbf0e223a84cbce3b9ca8ea9c889c80aa78d8c96588d34b0125ab18a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fo5pT0GjpxlWBdN0WeFw5kC/ZW/DQ37Aue/j1m3NJsGGfRy+1Z4/Jdxo/PDd+cqxKv7w8riv511qkB5w1o/HAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T00:15:42.302526Z","bundle_sha256":"d2ec5da9cf1394188aa078555a9eac05ce79a8f06e51fa803728e28af2bc03f7"}}