{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G3ZSAMCGBY2Y3P7BZOZG7ZORYH","short_pith_number":"pith:G3ZSAMCG","canonical_record":{"source":{"id":"2605.28710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T16:33:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4124077e1100442b55ebb80a363cbd916e0bc97061f5d8747b87c1136cd04b72","abstract_canon_sha256":"7dd010e0b904c6a8814f2b11ca2a5414000af73dcdb192422f21dac73f40c165"},"schema_version":"1.0"},"canonical_sha256":"36f32030460e358dbfe1cbb26fe5d1c1e9061421a7ff7d83932020e381fcfdbb","source":{"kind":"arxiv","id":"2605.28710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28710","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28710v1","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28710","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"G3ZSAMCGBY2Y","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"G3ZSAMCGBY2Y3P7B","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"G3ZSAMCG","created_at":"2026-05-28T02:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G3ZSAMCGBY2Y3P7BZOZG7ZORYH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T16:33:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4124077e1100442b55ebb80a363cbd916e0bc97061f5d8747b87c1136cd04b72","abstract_canon_sha256":"7dd010e0b904c6a8814f2b11ca2a5414000af73dcdb192422f21dac73f40c165"},"schema_version":"1.0"},"canonical_sha256":"36f32030460e358dbfe1cbb26fe5d1c1e9061421a7ff7d83932020e381fcfdbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:00.704574Z","signature_b64":"24VXLPMs3KYTSgoBQZ0FZB/3z4ESBJygogXn+bWmolEjPxwCAw6jznHw0s7R0q8UnyZk0nF3zC2P5pJF9WvfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36f32030460e358dbfe1cbb26fe5d1c1e9061421a7ff7d83932020e381fcfdbb","last_reissued_at":"2026-05-28T02:05:00.704142Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:00.704142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28710","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":"2026-05-28T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVXHn5UNBjxJHWfPak9RySYp0+p3NNxR0wH2SmtTOsPHJlPLswxeSr6o7r0CjslT+3k36U7l4078YdpEuAIhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:28:04.882537Z"},"content_sha256":"f298ed88331ecdf88c61d9c18cbe73f0ec7bf270f09dcda932b591755e6d5498","schema_version":"1.0","event_id":"sha256:f298ed88331ecdf88c61d9c18cbe73f0ec7bf270f09dcda932b591755e6d5498"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G3ZSAMCGBY2Y3P7BZOZG7ZORYH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aitor Soroa, Irune Zubiaga, Rodrigo Agerri","submitted_at":"2026-05-27T16:33:58Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the growing demand for multilingual evaluation, extending LLM-based evaluators to multilingual settings remains challenging, particularly for low-resource languages and scenarios where in-domain data is scarce. This work explores several strategies for developing multilingual LLMs-as-a-judge, considering whether in-domain data is available for fine-tuning or not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28710","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/2605.28710/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":"2026-05-28T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dmqlFnYs6laiX3mAlajyutalIRNDo3cLo6wiBgh2nd9VCbHDq0mzmbc/W+Lgd9vP+4y22xwmhEETqJfwVS2tCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:28:04.882922Z"},"content_sha256":"f47cea69a728e74293489131f278ec41b49701dd7065150a8eea200c879ff862","schema_version":"1.0","event_id":"sha256:f47cea69a728e74293489131f278ec41b49701dd7065150a8eea200c879ff862"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH/bundle.json","state_url":"https://pith.science/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH/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":"2026-06-05T09:28:04Z","links":{"resolver":"https://pith.science/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH","bundle":"https://pith.science/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH/bundle.json","state":"https://pith.science/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3ZSAMCGBY2Y3P7BZOZG7ZORYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G3ZSAMCGBY2Y3P7BZOZG7ZORYH","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":"7dd010e0b904c6a8814f2b11ca2a5414000af73dcdb192422f21dac73f40c165","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T16:33:58Z","title_canon_sha256":"4124077e1100442b55ebb80a363cbd916e0bc97061f5d8747b87c1136cd04b72"},"schema_version":"1.0","source":{"id":"2605.28710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28710","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28710v1","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28710","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"G3ZSAMCGBY2Y","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"G3ZSAMCGBY2Y3P7B","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"G3ZSAMCG","created_at":"2026-05-28T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:f47cea69a728e74293489131f278ec41b49701dd7065150a8eea200c879ff862","target":"graph","created_at":"2026-05-28T02:05:00Z","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/2605.28710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the growing demand for multilingual evaluation, extending LLM-based evaluators to multilingual settings remains challenging, particularly for low-resource languages and scenarios where in-domain data is scarce. This work explores several strategies for developing multilingual LLMs-as-a-judge, considering whether in-domain data is available for fine-tuning or not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and l","authors_text":"Aitor Soroa, Irune Zubiaga, Rodrigo Agerri","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T16:33:58Z","title":"Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28710","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:f298ed88331ecdf88c61d9c18cbe73f0ec7bf270f09dcda932b591755e6d5498","target":"record","created_at":"2026-05-28T02:05:00Z","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":"7dd010e0b904c6a8814f2b11ca2a5414000af73dcdb192422f21dac73f40c165","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T16:33:58Z","title_canon_sha256":"4124077e1100442b55ebb80a363cbd916e0bc97061f5d8747b87c1136cd04b72"},"schema_version":"1.0","source":{"id":"2605.28710","kind":"arxiv","version":1}},"canonical_sha256":"36f32030460e358dbfe1cbb26fe5d1c1e9061421a7ff7d83932020e381fcfdbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36f32030460e358dbfe1cbb26fe5d1c1e9061421a7ff7d83932020e381fcfdbb","first_computed_at":"2026-05-28T02:05:00.704142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:05:00.704142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"24VXLPMs3KYTSgoBQZ0FZB/3z4ESBJygogXn+bWmolEjPxwCAw6jznHw0s7R0q8UnyZk0nF3zC2P5pJF9WvfAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T02:05:00.704574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f298ed88331ecdf88c61d9c18cbe73f0ec7bf270f09dcda932b591755e6d5498","sha256:f47cea69a728e74293489131f278ec41b49701dd7065150a8eea200c879ff862"],"state_sha256":"77c402a4fb16145c8d372df02bcaf5ce1f6fc852e0dfd784235a018b0baf4376"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+mSNN4armquDt5rpsaqrW/N4k1d/uHgdv5GnahpMmdx3Cj+9peVAGhIDnh3JcinModcCkIStHK2yXKzE70gAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T09:28:04.885073Z","bundle_sha256":"df5c86d69b1f730030585cf6830e53ca018843ebdd9991974129705926499737"}}