{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I6PDZFARVVGR5YNLAQ2Y3FZTBO","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":"0000ce4906a24f728a48e783b1ed965cc703c493dd4a051b5121bed480d59b07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T06:04:55Z","title_canon_sha256":"282db59af1c616b5cf67501062a09148369a1934988db603f2f08c9f9eec036b"},"schema_version":"1.0","source":{"id":"2410.17578","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17578","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17578v2","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17578","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"I6PDZFARVVGR","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"I6PDZFARVVGR5YNL","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"I6PDZFAR","created_at":"2026-07-05T10:41:16Z"}],"graph_snapshots":[{"event_id":"sha256:0843b28383c4dce8127d65b55f56a6b474b58f3c743ffa1c075f400a604426cd","target":"graph","created_at":"2026-07-05T10:41:16Z","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/2410.17578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) are now capable of producing fluent and coherent content in languages other than English, it is not imperative to precisely evaluate these non-English outputs. However, when assessing the outputs from mutlilingual LLMs, prior works often employed LLM based evaluators that excel at assessing English outputs, without a thorough examination of whether these evaluators could effectively assess non-English text as well. Moreover, existing benchmarks to test evaluator LLMs (referred to as \"meta-evaluation benchmarks\") are mostly English-centric. To bridge this gap and","authors_text":"Dongkeun Yoon, Guijin Son, Jaume Prats-Cristi\\`a, Javier Aula-Blasco, Juyoung Suk, Luc\\'ia Tormo-Ba\\~nuelos, Mano Aslan, Seungone Kim, Shayekh Bin Islam, Vu Trong Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T06:04:55Z","title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17578","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":"sha256:7a742d9c8ac056c9cc7b471f86bfd80a82ae55a71fe48248144c9b13b06c5794","target":"record","created_at":"2026-07-05T10:41:16Z","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":"0000ce4906a24f728a48e783b1ed965cc703c493dd4a051b5121bed480d59b07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T06:04:55Z","title_canon_sha256":"282db59af1c616b5cf67501062a09148369a1934988db603f2f08c9f9eec036b"},"schema_version":"1.0","source":{"id":"2410.17578","kind":"arxiv","version":2}},"canonical_sha256":"479e3c9411ad4d1ee1ab04358d97330bb567ded26d107bffbd07e009fc121404","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"479e3c9411ad4d1ee1ab04358d97330bb567ded26d107bffbd07e009fc121404","first_computed_at":"2026-07-05T10:41:16.413213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:16.413213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rBH/0wIZ9N3bZDPZSbLe7/xo2MoBNgsJs7GzWZCmfMoIRFVT1NOSnqAGddxYj0jtfgRQ13DzyvNXBFtkQ+mXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:16.413807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17578","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a742d9c8ac056c9cc7b471f86bfd80a82ae55a71fe48248144c9b13b06c5794","sha256:0843b28383c4dce8127d65b55f56a6b474b58f3c743ffa1c075f400a604426cd"],"state_sha256":"33ad888c2729e2d1ba42c3bee27eda86ea0f67783559b09e5318c18a9573638d"}