{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2TNBA5VSMYHNII3VS2FSMVVHL7","short_pith_number":"pith:2TNBA5VS","canonical_record":{"source":{"id":"2505.21999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T06:00:21Z","cross_cats_sorted":[],"title_canon_sha256":"71b532bae8dfc610a3f9b78ae78c21e424bf087e7d3536c868de6df3dadb2434","abstract_canon_sha256":"aaa856421067b98c7a80a538ab1c5ad13bdeb7e4f574a3a549599fbdba593119"},"schema_version":"1.0"},"canonical_sha256":"d4da1076b2660ed42375968b2656a75fc302dd89b51733383e0ebea397d3bab8","source":{"kind":"arxiv","id":"2505.21999","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21999","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21999v1","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21999","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"2TNBA5VSMYHN","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"2TNBA5VSMYHNII3V","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"2TNBA5VS","created_at":"2026-07-05T11:11:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2TNBA5VSMYHNII3VS2FSMVVHL7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T06:00:21Z","cross_cats_sorted":[],"title_canon_sha256":"71b532bae8dfc610a3f9b78ae78c21e424bf087e7d3536c868de6df3dadb2434","abstract_canon_sha256":"aaa856421067b98c7a80a538ab1c5ad13bdeb7e4f574a3a549599fbdba593119"},"schema_version":"1.0"},"canonical_sha256":"d4da1076b2660ed42375968b2656a75fc302dd89b51733383e0ebea397d3bab8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:07.638780Z","signature_b64":"u9XEUEzYgEjlqPn1khimspthNcoJs/V3fhioCrMSUaxHjP9XBSAb5L/4488ovM4jfq6JVdtXvaDuuq8LD1HOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4da1076b2660ed42375968b2656a75fc302dd89b51733383e0ebea397d3bab8","last_reissued_at":"2026-07-05T11:11:07.638228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:07.638228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21999","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":"2026-07-05T11:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4C81YqP2z1J/xQ1JnvTpLRqWp4ukHGMDhru0b8E5dh21QpnVOOj/D/TZXOo4sVh0a4QEBJ8nTNBrIEVOTjaLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:29:16.907937Z"},"content_sha256":"202df3f5136e93b9937d2445649d93f6bf61b19f4a8e084d556936d0be29fd4a","schema_version":"1.0","event_id":"sha256:202df3f5136e93b9937d2445649d93f6bf61b19f4a8e084d556936d0be29fd4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2TNBA5VSMYHNII3VS2FSMVVHL7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashim Gupta, Maitrey Mehta, Vivek Srikumar, Zhichao Xu","submitted_at":"2025-05-28T06:00:21Z","abstract_excerpt":"Large language models (LLMs) provide detailed and impressive responses to queries in English. However, are they really consistent at responding to the same query in other languages? The popular way of evaluating for multilingual performance of LLMs requires expensive-to-collect annotated datasets. Further, evaluating for tasks like open-ended generation, where multiple correct answers may exist, is nontrivial. Instead, we propose to evaluate the predictability of model response across different languages. In this work, we propose a framework to evaluate LLM's cross-lingual consistency based on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21999","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/2505.21999/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":"2026-07-05T11:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIEiQTWLBd8grO44LlLXmwAmCoCWv1WC198ZcaDMeZXh/whLXWlN+KhnRWOqOdk3Ux73dPaC+v5WP1F72fMWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:29:16.908438Z"},"content_sha256":"98f8e0ec49f4a240d20d16c775085071bde9762f5369736bdf7381222e51ed84","schema_version":"1.0","event_id":"sha256:98f8e0ec49f4a240d20d16c775085071bde9762f5369736bdf7381222e51ed84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TNBA5VSMYHNII3VS2FSMVVHL7/bundle.json","state_url":"https://pith.science/pith/2TNBA5VSMYHNII3VS2FSMVVHL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TNBA5VSMYHNII3VS2FSMVVHL7/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":"2026-08-06T03:29:16Z","links":{"resolver":"https://pith.science/pith/2TNBA5VSMYHNII3VS2FSMVVHL7","bundle":"https://pith.science/pith/2TNBA5VSMYHNII3VS2FSMVVHL7/bundle.json","state":"https://pith.science/pith/2TNBA5VSMYHNII3VS2FSMVVHL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TNBA5VSMYHNII3VS2FSMVVHL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2TNBA5VSMYHNII3VS2FSMVVHL7","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":"aaa856421067b98c7a80a538ab1c5ad13bdeb7e4f574a3a549599fbdba593119","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T06:00:21Z","title_canon_sha256":"71b532bae8dfc610a3f9b78ae78c21e424bf087e7d3536c868de6df3dadb2434"},"schema_version":"1.0","source":{"id":"2505.21999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21999","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21999v1","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21999","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"2TNBA5VSMYHN","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"2TNBA5VSMYHNII3V","created_at":"2026-07-05T11:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"2TNBA5VS","created_at":"2026-07-05T11:11:07Z"}],"graph_snapshots":[{"event_id":"sha256:98f8e0ec49f4a240d20d16c775085071bde9762f5369736bdf7381222e51ed84","target":"graph","created_at":"2026-07-05T11:11:07Z","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/2505.21999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) provide detailed and impressive responses to queries in English. However, are they really consistent at responding to the same query in other languages? The popular way of evaluating for multilingual performance of LLMs requires expensive-to-collect annotated datasets. Further, evaluating for tasks like open-ended generation, where multiple correct answers may exist, is nontrivial. Instead, we propose to evaluate the predictability of model response across different languages. In this work, we propose a framework to evaluate LLM's cross-lingual consistency based on","authors_text":"Ashim Gupta, Maitrey Mehta, Vivek Srikumar, Zhichao Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T06:00:21Z","title":"Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21999","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":"sha256:202df3f5136e93b9937d2445649d93f6bf61b19f4a8e084d556936d0be29fd4a","target":"record","created_at":"2026-07-05T11:11:07Z","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":"aaa856421067b98c7a80a538ab1c5ad13bdeb7e4f574a3a549599fbdba593119","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T06:00:21Z","title_canon_sha256":"71b532bae8dfc610a3f9b78ae78c21e424bf087e7d3536c868de6df3dadb2434"},"schema_version":"1.0","source":{"id":"2505.21999","kind":"arxiv","version":1}},"canonical_sha256":"d4da1076b2660ed42375968b2656a75fc302dd89b51733383e0ebea397d3bab8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4da1076b2660ed42375968b2656a75fc302dd89b51733383e0ebea397d3bab8","first_computed_at":"2026-07-05T11:11:07.638228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:07.638228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u9XEUEzYgEjlqPn1khimspthNcoJs/V3fhioCrMSUaxHjP9XBSAb5L/4488ovM4jfq6JVdtXvaDuuq8LD1HOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:07.638780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:202df3f5136e93b9937d2445649d93f6bf61b19f4a8e084d556936d0be29fd4a","sha256:98f8e0ec49f4a240d20d16c775085071bde9762f5369736bdf7381222e51ed84"],"state_sha256":"809e69cc0e37fbe3efc8c475fec1c01460a1b011090b936948a55fc7ee56cbb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7Nem/YiFhwr2fSwtHOuqLSHcnk+buAIB3SYMLupjPzmNCTja7n3+AvSTjrzP4kRG1Z0JSCPTapKOrgHoSeICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:29:16.912546Z","bundle_sha256":"144e586cd1d339fda126bd6a289d8856139d4ae5f35af1e04306505c7a058d08"}}