{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EFXJ3EBL3MQ7I6MCCJFMJE6RNV","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":"cf98ad6cae354cd8b408bb1a8a070f196f6642f358c2caa3de622fe3989e3246","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T06:41:58Z","title_canon_sha256":"6da735c07a08a98c7eeab1f561e1386b64712b678ef4cf2411e34b0069df555e"},"schema_version":"1.0","source":{"id":"2309.07462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07462","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07462v2","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07462","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"EFXJ3EBL3MQ7","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"EFXJ3EBL3MQ7I6MC","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"EFXJ3EBL","created_at":"2026-07-05T07:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:276143d14a32588ebb96576c44906dd773dee1e5c5fc7500cd85da8bba20f8c7","target":"graph","created_at":"2026-07-05T07:44:20Z","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/2309.07462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) excel in various Natural Language Processing (NLP) tasks, yet their evaluation, particularly in languages beyond the top $20$, remains inadequate due to existing benchmarks and metrics limitations. Employing LLMs as evaluators to rank or score other models' outputs emerges as a viable solution, addressing the constraints tied to human annotators and established benchmarks. In this study, we explore the potential of LLM-based evaluators, specifically GPT-4 in enhancing multilingual evaluation by calibrating them against $20$K human judgments across three text-genera","authors_text":"Adrian de Wynter, Harshita Diddee, Kalika Bali, Mohamed Ahmed, Monojit Choudhury, Rishav Hada, Sunayana Sitaram, Varun Gumma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T06:41:58Z","title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07462","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":"sha256:7f2495894e7f8eefb5f91bada309d89700bab4d2f42a25d6428976ea97f33245","target":"record","created_at":"2026-07-05T07:44:20Z","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":"cf98ad6cae354cd8b408bb1a8a070f196f6642f358c2caa3de622fe3989e3246","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T06:41:58Z","title_canon_sha256":"6da735c07a08a98c7eeab1f561e1386b64712b678ef4cf2411e34b0069df555e"},"schema_version":"1.0","source":{"id":"2309.07462","kind":"arxiv","version":2}},"canonical_sha256":"216e9d902bdb21f47982124ac493d16d738b4d765682b82e2e5b16e09e50520d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"216e9d902bdb21f47982124ac493d16d738b4d765682b82e2e5b16e09e50520d","first_computed_at":"2026-07-05T07:44:20.273155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:20.273155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kk6oh/kxIx8MX6wv0ph+JNmXy0TN3owIG7DQdQs4Mvqx0N2mArcNzMZ7bFN38TXjs7+ZKuQ4gWVscv0EFK4OBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:20.273663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f2495894e7f8eefb5f91bada309d89700bab4d2f42a25d6428976ea97f33245","sha256:276143d14a32588ebb96576c44906dd773dee1e5c5fc7500cd85da8bba20f8c7"],"state_sha256":"25a2a60133a92945bc9b94aef12840b8b066388dd617b7a7acaf6756895b24d0"}