{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G2CPE7YD44UNDSOGXGXMICXGCR","short_pith_number":"pith:G2CPE7YD","schema_version":"1.0","canonical_sha256":"3684f27f03e728d1c9c6b9aec40ae6147eafc0fce6066ec4e7735479674a41e6","source":{"kind":"arxiv","id":"2409.01790","version":2},"attestation_state":"computed","paper":{"title":"Training on the Benchmark Is Not All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengming Li, Jia Zhu, Min Yang, Ruifeng Xu, Shiwen Ni, Xiangtao Kong, Xiping Hu","submitted_at":"2024-09-03T11:09:44Z","abstract_excerpt":"The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests to become unreliable. If any model has been trained on a benchmark test set, it can seriously hinder the health of the field. In order to automate and efficiently test the capabilities of large language models, numerous mainstream benchmarks adopt a multiple-choice format. As the swapping of the contents of multiple-choice options does not affect the meaning "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.01790","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T11:09:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"210f4dca534e726f1092f25e1de1436752c1d34d5fc794184b0936933e2f9856","abstract_canon_sha256":"40d41d4033ef1335e639ca898ca9631088442a7454a51197782faee5ae780cb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:22.659678Z","signature_b64":"GGHb1ElEJl5fpH59BHElFtCu5Ij88+jiUbQ/XjDGhQrvwga7KijioYJZIrZRzsLg5dv9q6+ALv1Qu3S3ktu7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3684f27f03e728d1c9c6b9aec40ae6147eafc0fce6066ec4e7735479674a41e6","last_reissued_at":"2026-07-05T10:21:22.659087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:22.659087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training on the Benchmark Is Not All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengming Li, Jia Zhu, Min Yang, Ruifeng Xu, Shiwen Ni, Xiangtao Kong, Xiping Hu","submitted_at":"2024-09-03T11:09:44Z","abstract_excerpt":"The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests to become unreliable. If any model has been trained on a benchmark test set, it can seriously hinder the health of the field. In order to automate and efficiently test the capabilities of large language models, numerous mainstream benchmarks adopt a multiple-choice format. As the swapping of the contents of multiple-choice options does not affect the meaning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01790","kind":"arxiv","version":2},"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/2409.01790/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.01790","created_at":"2026-07-05T10:21:22.659189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01790v2","created_at":"2026-07-05T10:21:22.659189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01790","created_at":"2026-07-05T10:21:22.659189+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2CPE7YD44UN","created_at":"2026-07-05T10:21:22.659189+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2CPE7YD44UNDSOG","created_at":"2026-07-05T10:21:22.659189+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2CPE7YD","created_at":"2026-07-05T10:21:22.659189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR","json":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR.json","graph_json":"https://pith.science/api/pith-number/G2CPE7YD44UNDSOGXGXMICXGCR/graph.json","events_json":"https://pith.science/api/pith-number/G2CPE7YD44UNDSOGXGXMICXGCR/events.json","paper":"https://pith.science/paper/G2CPE7YD"},"agent_actions":{"view_html":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR","download_json":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR.json","view_paper":"https://pith.science/paper/G2CPE7YD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01790&json=true","fetch_graph":"https://pith.science/api/pith-number/G2CPE7YD44UNDSOGXGXMICXGCR/graph.json","fetch_events":"https://pith.science/api/pith-number/G2CPE7YD44UNDSOGXGXMICXGCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR/action/storage_attestation","attest_author":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR/action/author_attestation","sign_citation":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR/action/citation_signature","submit_replication":"https://pith.science/pith/G2CPE7YD44UNDSOGXGXMICXGCR/action/replication_record"}},"created_at":"2026-07-05T10:21:22.659189+00:00","updated_at":"2026-07-05T10:21:22.659189+00:00"}