{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PNHPTCMOGDQ7VFOU4SMAABS6EA","short_pith_number":"pith:PNHPTCMO","canonical_record":{"source":{"id":"2311.01964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:59:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b51e749f13a6ed8b8dc147dbe8f97d8d27ff1e9506bfd9db2f7708fb0985174e","abstract_canon_sha256":"ee518a6f37115a8465966dbf5af2dcae55d472bacbb6ec64dfa54f7f377ab68a"},"schema_version":"1.0"},"canonical_sha256":"7b4ef9898e30e1fa95d4e49800065e20240cbc0e444b5982b90d7a67ce963910","source":{"kind":"arxiv","id":"2311.01964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01964","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01964v1","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01964","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"PNHPTCMOGDQ7","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"PNHPTCMOGDQ7VFOU","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"PNHPTCMO","created_at":"2026-07-05T07:08:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PNHPTCMOGDQ7VFOU4SMAABS6EA","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:59:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b51e749f13a6ed8b8dc147dbe8f97d8d27ff1e9506bfd9db2f7708fb0985174e","abstract_canon_sha256":"ee518a6f37115a8465966dbf5af2dcae55d472bacbb6ec64dfa54f7f377ab68a"},"schema_version":"1.0"},"canonical_sha256":"7b4ef9898e30e1fa95d4e49800065e20240cbc0e444b5982b90d7a67ce963910","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:48.050903Z","signature_b64":"pBcZ9+serCtHozq21dDOj6MxZYYnP35m5XTKv8MjbU4pZ5Anw2b/s6yuRRCc4kidV1p2K0zTXtIegXnU8ri+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b4ef9898e30e1fa95d4e49800065e20240cbc0e444b5982b90d7a67ce963910","last_reissued_at":"2026-07-05T07:08:48.050422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:48.050422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01964","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0iftDY/Ke9rTFtGdYrsQr1cn/aIK3mvYddPCQd4du7Uwut6M4WQfD5PvvRG0xs6ZV7E+I2lFFgRPT0zoqMgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:05:42.106371Z"},"content_sha256":"8387d9746c89900ecb9a97d1c6438c9668554400b1ab6c79b6097dfaa636caed","schema_version":"1.0","event_id":"sha256:8387d9746c89900ecb9a97d1c6438c9668554400b1ab6c79b6097dfaa636caed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PNHPTCMOGDQ7VFOU4SMAABS6EA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Make Your LLM an Evaluation Benchmark Cheater","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao, Wentong Chen, Xu Chen, Yankai Lin, Yutao Zhu, Zhipeng Chen","submitted_at":"2023-11-03T14:59:54Z","abstract_excerpt":"Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs in different aspects. Despite that a number of high-quality benchmarks have been released, the concerns about the appropriate use of these benchmarks and the fair comparison of different models are increasingly growing. Considering these concerns, in this paper, we discuss the potential risk and impact of inappropriately us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01964","kind":"arxiv","version":1},"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/2311.01964/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":"2026-07-05T07:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1lfI7KLl+6pNu2ZkTXb+A1OwcsixLayMf823DZu5WvZ5urd/2YtaCi5PcSUJMzhkfX6fZXeffZMrji+4LU4NCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:05:42.107150Z"},"content_sha256":"9fcd6bf7549bbd04f51eb6e8f79ddb31fffdd6a6beef33d341cb73a4843bc362","schema_version":"1.0","event_id":"sha256:9fcd6bf7549bbd04f51eb6e8f79ddb31fffdd6a6beef33d341cb73a4843bc362"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA/bundle.json","state_url":"https://pith.science/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA/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":"2026-08-07T06:05:42Z","links":{"resolver":"https://pith.science/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA","bundle":"https://pith.science/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA/bundle.json","state":"https://pith.science/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNHPTCMOGDQ7VFOU4SMAABS6EA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PNHPTCMOGDQ7VFOU4SMAABS6EA","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":"ee518a6f37115a8465966dbf5af2dcae55d472bacbb6ec64dfa54f7f377ab68a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:59:54Z","title_canon_sha256":"b51e749f13a6ed8b8dc147dbe8f97d8d27ff1e9506bfd9db2f7708fb0985174e"},"schema_version":"1.0","source":{"id":"2311.01964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01964","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01964v1","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01964","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"PNHPTCMOGDQ7","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"PNHPTCMOGDQ7VFOU","created_at":"2026-07-05T07:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"PNHPTCMO","created_at":"2026-07-05T07:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:9fcd6bf7549bbd04f51eb6e8f79ddb31fffdd6a6beef33d341cb73a4843bc362","target":"graph","created_at":"2026-07-05T07:08:48Z","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/2311.01964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs in different aspects. Despite that a number of high-quality benchmarks have been released, the concerns about the appropriate use of these benchmarks and the fair comparison of different models are increasingly growing. Considering these concerns, in this paper, we discuss the potential risk and impact of inappropriately us","authors_text":"Jiawei Han, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao, Wentong Chen, Xu Chen, Yankai Lin, Yutao Zhu, Zhipeng Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:59:54Z","title":"Don't Make Your LLM an Evaluation Benchmark Cheater"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01964","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":"sha256:8387d9746c89900ecb9a97d1c6438c9668554400b1ab6c79b6097dfaa636caed","target":"record","created_at":"2026-07-05T07:08:48Z","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":"ee518a6f37115a8465966dbf5af2dcae55d472bacbb6ec64dfa54f7f377ab68a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:59:54Z","title_canon_sha256":"b51e749f13a6ed8b8dc147dbe8f97d8d27ff1e9506bfd9db2f7708fb0985174e"},"schema_version":"1.0","source":{"id":"2311.01964","kind":"arxiv","version":1}},"canonical_sha256":"7b4ef9898e30e1fa95d4e49800065e20240cbc0e444b5982b90d7a67ce963910","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b4ef9898e30e1fa95d4e49800065e20240cbc0e444b5982b90d7a67ce963910","first_computed_at":"2026-07-05T07:08:48.050422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:48.050422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pBcZ9+serCtHozq21dDOj6MxZYYnP35m5XTKv8MjbU4pZ5Anw2b/s6yuRRCc4kidV1p2K0zTXtIegXnU8ri+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:48.050903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8387d9746c89900ecb9a97d1c6438c9668554400b1ab6c79b6097dfaa636caed","sha256:9fcd6bf7549bbd04f51eb6e8f79ddb31fffdd6a6beef33d341cb73a4843bc362"],"state_sha256":"83e0e0a8ad4b30ad0f46e35c5af62c4cd8a56ddf7ab6470023aff633344aa6b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JYApNCYhYICk5j5G1cBmT+lUUt3OwwKL3yaBFKBr0YgV+zBgybqNGMAdeJoyO5wxtglxiQw/6WtIzHr1lJvrBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:05:42.112190Z","bundle_sha256":"a7119f89ca3cffceebfeb25d6130cd04862aea7be32eba93e64c6d8a61834ab8"}}