{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TXX7EPSSER3FQZRMCQ44QGLSSW","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":"1ed1b11e5bf4ced129a3781d186000f2bcf450127d945e8833daa3adce4f9c2d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T01:01:02Z","title_canon_sha256":"3532184b226d340d1a4055765c3f6ffaf3a0aab2308cf5c03d2e75499cfd71b8"},"schema_version":"1.0","source":{"id":"2502.18339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18339","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18339v1","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18339","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"TXX7EPSSER3F","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"TXX7EPSSER3FQZRM","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"TXX7EPSS","created_at":"2026-07-05T10:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:45943c514d7392e38b36b438f9034aa53adf43ea202abb50fe88aa9b49f723fa","target":"graph","created_at":"2026-07-05T10:19:52Z","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/2502.18339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The explosion of high-performing conversational language models (LMs) has spurred a shift from classic natural language processing (NLP) benchmarks to expensive, time-consuming and noisy human evaluations - yet the relationship between these two evaluation strategies remains hazy. In this paper, we conduct a large-scale study of four Chat Llama 2 models, comparing their performance on 160 standard NLP benchmarks (e.g., MMLU, ARC, BIG-Bench Hard) against extensive human preferences on more than 11k single-turn and 2k multi-turn dialogues from over 2k human annotators. Our findings are striking:","authors_text":"Aaditya K Singh, Binh Tang, Dieuwke Hupkes, Lovish Madaan, Niladri S. Chatterji, Prajjwal Bhargava, Punit Singh Koura, Ranjan Subramanian, Rylan Schaeffer, Sanmi Koyejo, Sergey Edunov, Sharan Narang, Todor Mihaylov, Vedanuj Goswami","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T01:01:02Z","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18339","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:a2d16eef9fd12d10f153f78665e6a45c9897c50c0d9fa6272c78fff8afc3ed24","target":"record","created_at":"2026-07-05T10:19:52Z","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":"1ed1b11e5bf4ced129a3781d186000f2bcf450127d945e8833daa3adce4f9c2d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T01:01:02Z","title_canon_sha256":"3532184b226d340d1a4055765c3f6ffaf3a0aab2308cf5c03d2e75499cfd71b8"},"schema_version":"1.0","source":{"id":"2502.18339","kind":"arxiv","version":1}},"canonical_sha256":"9deff23e52247658662c1439c81972958d2a1490844289db15fec19609332719","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9deff23e52247658662c1439c81972958d2a1490844289db15fec19609332719","first_computed_at":"2026-07-05T10:19:52.506915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:52.506915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FLBKBhnIzbeg+6okCYG/xPo2ThHvV2i0ITzOvLCzMEXwGV0LGEeDee2hFxSJqPQ0nB2QCC8SOt6upuePB9ojDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:52.507403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2d16eef9fd12d10f153f78665e6a45c9897c50c0d9fa6272c78fff8afc3ed24","sha256:45943c514d7392e38b36b438f9034aa53adf43ea202abb50fe88aa9b49f723fa"],"state_sha256":"74dceb53fd5fc100899efcebbed03595f8a0430a7f72e1b48bbf3bb0159b2a33"}