{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KERZ3COJQGIOIJFCAS6QLVAXP3","short_pith_number":"pith:KERZ3COJ","canonical_record":{"source":{"id":"2607.14480","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T01:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"acd776553876caa24ebec736039a1724e01bac111b422f293f60eb87deb4c56f","abstract_canon_sha256":"3e74ef9c59484a32c4a8144ead1a37be3602d1ba9976cfe33cc6bb1385ec4756"},"schema_version":"1.0"},"canonical_sha256":"51239d89c98190e424a204bd05d4177ec8ce2bed1bb07196604fe9364e01a29e","source":{"kind":"arxiv","id":"2607.14480","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14480","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14480v1","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14480","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"pith_short_12","alias_value":"KERZ3COJQGIO","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"pith_short_16","alias_value":"KERZ3COJQGIOIJFC","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"pith_short_8","alias_value":"KERZ3COJ","created_at":"2026-07-17T00:21:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KERZ3COJQGIOIJFCAS6QLVAXP3","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14480","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T01:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"acd776553876caa24ebec736039a1724e01bac111b422f293f60eb87deb4c56f","abstract_canon_sha256":"3e74ef9c59484a32c4a8144ead1a37be3602d1ba9976cfe33cc6bb1385ec4756"},"schema_version":"1.0"},"canonical_sha256":"51239d89c98190e424a204bd05d4177ec8ce2bed1bb07196604fe9364e01a29e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:14.627116Z","signature_b64":"ET4zibiUQolQLB7831awVrJ/0vpgyJGpbhLkhr+v6XnYNerYtYrPakSW8cSc+FgQ6tjtSBjtx1iaiZIAJplvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51239d89c98190e424a204bd05d4177ec8ce2bed1bb07196604fe9364e01a29e","last_reissued_at":"2026-07-17T00:21:14.626255Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:14.626255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14480","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":"2026-07-17T00:21:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXzweZN+tdpGOdsiZDnvLOHqttnbQkKmDZf9ieALM/xEvmM1kNlUlwwmyDnLBThdaEQg/dv8Ky4hCUBjoAPQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:53:02.759413Z"},"content_sha256":"b6a93184a2a79eff75871127f26f63aa76a86f36b7d064d53a8f7a5bb025403a","schema_version":"1.0","event_id":"sha256:b6a93184a2a79eff75871127f26f63aa76a86f36b7d064d53a8f7a5bb025403a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KERZ3COJQGIOIJFCAS6QLVAXP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM Evaluators are Biased across Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Ej Zhou, Lucas Resck, Zheng Hui","submitted_at":"2026-07-16T01:53:09Z","abstract_excerpt":"LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct experiments with semantically identical instruction-response pairs across 23 languages, and find that multilingual evaluators assign significantly different scores to different evaluation languages. The bias is statistically significant and consistent across eight open-weight evaluators of different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14480","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/2607.14480/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":"2026-07-17T00:21:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XOf5qeOf73JvDEjrb4VWSoHllWB+MJlrmtW43SEl1oQuUq/OWBuxcUhBoqspZaaM+MxMRoTcsNDMGqwICHukCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:53:02.759955Z"},"content_sha256":"201dc14024f0ab08788736de591909a59995d703fa4e4668cd7e223521a3e2d5","schema_version":"1.0","event_id":"sha256:201dc14024f0ab08788736de591909a59995d703fa4e4668cd7e223521a3e2d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KERZ3COJQGIOIJFCAS6QLVAXP3/bundle.json","state_url":"https://pith.science/pith/KERZ3COJQGIOIJFCAS6QLVAXP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KERZ3COJQGIOIJFCAS6QLVAXP3/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":"2026-08-05T23:53:02Z","links":{"resolver":"https://pith.science/pith/KERZ3COJQGIOIJFCAS6QLVAXP3","bundle":"https://pith.science/pith/KERZ3COJQGIOIJFCAS6QLVAXP3/bundle.json","state":"https://pith.science/pith/KERZ3COJQGIOIJFCAS6QLVAXP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KERZ3COJQGIOIJFCAS6QLVAXP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KERZ3COJQGIOIJFCAS6QLVAXP3","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":"3e74ef9c59484a32c4a8144ead1a37be3602d1ba9976cfe33cc6bb1385ec4756","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T01:53:09Z","title_canon_sha256":"acd776553876caa24ebec736039a1724e01bac111b422f293f60eb87deb4c56f"},"schema_version":"1.0","source":{"id":"2607.14480","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14480","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14480v1","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14480","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"pith_short_12","alias_value":"KERZ3COJQGIO","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"pith_short_16","alias_value":"KERZ3COJQGIOIJFC","created_at":"2026-07-17T00:21:14Z"},{"alias_kind":"pith_short_8","alias_value":"KERZ3COJ","created_at":"2026-07-17T00:21:14Z"}],"graph_snapshots":[{"event_id":"sha256:201dc14024f0ab08788736de591909a59995d703fa4e4668cd7e223521a3e2d5","target":"graph","created_at":"2026-07-17T00:21:14Z","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/2607.14480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct experiments with semantically identical instruction-response pairs across 23 languages, and find that multilingual evaluators assign significantly different scores to different evaluation languages. The bias is statistically significant and consistent across eight open-weight evaluators of different","authors_text":"Anna Korhonen, Ej Zhou, Lucas Resck, Zheng Hui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T01:53:09Z","title":"LLM Evaluators are Biased across Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14480","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:b6a93184a2a79eff75871127f26f63aa76a86f36b7d064d53a8f7a5bb025403a","target":"record","created_at":"2026-07-17T00:21:14Z","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":"3e74ef9c59484a32c4a8144ead1a37be3602d1ba9976cfe33cc6bb1385ec4756","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T01:53:09Z","title_canon_sha256":"acd776553876caa24ebec736039a1724e01bac111b422f293f60eb87deb4c56f"},"schema_version":"1.0","source":{"id":"2607.14480","kind":"arxiv","version":1}},"canonical_sha256":"51239d89c98190e424a204bd05d4177ec8ce2bed1bb07196604fe9364e01a29e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51239d89c98190e424a204bd05d4177ec8ce2bed1bb07196604fe9364e01a29e","first_computed_at":"2026-07-17T00:21:14.626255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:21:14.626255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ET4zibiUQolQLB7831awVrJ/0vpgyJGpbhLkhr+v6XnYNerYtYrPakSW8cSc+FgQ6tjtSBjtx1iaiZIAJplvCQ==","signature_status":"signed_v1","signed_at":"2026-07-17T00:21:14.627116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14480","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a93184a2a79eff75871127f26f63aa76a86f36b7d064d53a8f7a5bb025403a","sha256:201dc14024f0ab08788736de591909a59995d703fa4e4668cd7e223521a3e2d5"],"state_sha256":"3285ce1bd0144ba2dd0558655607d853287adc97ea8f10cbde6018dd3c52236f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/ElahPTHJb3CBohrQ1RwtN5mWLhdYt4gCLLIrqSdKlrW8PK1CV15iWMypYCG6qMzM8G2cMleQZi8WJTt8owAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:53:02.764184Z","bundle_sha256":"764479ec2319d2ada32d1c6142dd9b24377079b963ce78d7a38da8fe3123e7e5"}}