{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2JVDJNLJ57AENYAQYOGE6XNCNC","short_pith_number":"pith:2JVDJNLJ","canonical_record":{"source":{"id":"2410.15956","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T12:34:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19d5bfdc940414c9f0798c33a9663586b728c7438600bdc7b1094593ada641d8","abstract_canon_sha256":"b43c8df27e7e4874e50a09b133d947fa7c73b88210cc4623b580eaa22e996141"},"schema_version":"1.0"},"canonical_sha256":"d26a34b569efc046e010c38c4f5da2688af63ae59c634449b3504542b1220c34","source":{"kind":"arxiv","id":"2410.15956","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15956","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15956v3","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15956","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"2JVDJNLJ57AE","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"2JVDJNLJ57AENYAQ","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"2JVDJNLJ","created_at":"2026-07-05T11:43:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2JVDJNLJ57AENYAQYOGE6XNCNC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15956","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T12:34:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19d5bfdc940414c9f0798c33a9663586b728c7438600bdc7b1094593ada641d8","abstract_canon_sha256":"b43c8df27e7e4874e50a09b133d947fa7c73b88210cc4623b580eaa22e996141"},"schema_version":"1.0"},"canonical_sha256":"d26a34b569efc046e010c38c4f5da2688af63ae59c634449b3504542b1220c34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:29.570049Z","signature_b64":"wfbyQsf36iv16w+xLZ82itxeU2TbuS1S6p4+j/vNm2BBFrHMPHFBLg6eGkAJDKMPIm2WS5fSSYlnLnwEneKsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d26a34b569efc046e010c38c4f5da2688af63ae59c634449b3504542b1220c34","last_reissued_at":"2026-07-05T11:43:29.569500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:29.569500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15956","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIhZ+l8YB4d4JbpkG9fxaeRQ8HPu2bX+3dX8J5bKNgIPmgBg7Ei7CYJJ4LaG8WfsPB+FsuEfyEGH7qySz76CCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:59.314158Z"},"content_sha256":"33d5664a9cd3ac206c7fb0e0504b5f0a7436ff903ae2c46b59e6016c94bcd30a","schema_version":"1.0","event_id":"sha256:33d5664a9cd3ac206c7fb0e0504b5f0a7436ff903ae2c46b59e6016c94bcd30a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2JVDJNLJ57AENYAQYOGE6XNCNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Henry Xiao, Min Li, Saloni Potdar, Simone Conia, Yanzhu Guo, Zelin Zhou","submitted_at":"2024-10-21T12:34:17Z","abstract_excerpt":"Current Large Language Models (LLMs) are predominantly designed with English as the primary language, and even the few that are multilingual tend to exhibit strong English-centric biases. Much like speakers who might produce awkward expressions when learning a second language, LLMs often generate unnatural outputs in non-English languages, reflecting English-centric patterns in both vocabulary and grammar. Despite the importance of this issue, the naturalness of multilingual LLM outputs has received limited attention. In this paper, we address this gap by introducing novel automatic corpus-lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15956","kind":"arxiv","version":3},"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/2410.15956/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":"2026-07-05T11:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yOeImeZBuGLSSscYaclr3GlIwJdznzFKWOOnJ9nbnX/+lSmk32NiwEZq42P81ytOW0PlQBCJlYDHxJQ4InHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:59.314645Z"},"content_sha256":"09e345788511b028827bbefc344295405c5044aef8d792d89bea1824288d0497","schema_version":"1.0","event_id":"sha256:09e345788511b028827bbefc344295405c5044aef8d792d89bea1824288d0497"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JVDJNLJ57AENYAQYOGE6XNCNC/bundle.json","state_url":"https://pith.science/pith/2JVDJNLJ57AENYAQYOGE6XNCNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JVDJNLJ57AENYAQYOGE6XNCNC/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":"2026-08-10T06:23:59Z","links":{"resolver":"https://pith.science/pith/2JVDJNLJ57AENYAQYOGE6XNCNC","bundle":"https://pith.science/pith/2JVDJNLJ57AENYAQYOGE6XNCNC/bundle.json","state":"https://pith.science/pith/2JVDJNLJ57AENYAQYOGE6XNCNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JVDJNLJ57AENYAQYOGE6XNCNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2JVDJNLJ57AENYAQYOGE6XNCNC","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":"b43c8df27e7e4874e50a09b133d947fa7c73b88210cc4623b580eaa22e996141","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T12:34:17Z","title_canon_sha256":"19d5bfdc940414c9f0798c33a9663586b728c7438600bdc7b1094593ada641d8"},"schema_version":"1.0","source":{"id":"2410.15956","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15956","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15956v3","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15956","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"2JVDJNLJ57AE","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"2JVDJNLJ57AENYAQ","created_at":"2026-07-05T11:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"2JVDJNLJ","created_at":"2026-07-05T11:43:29Z"}],"graph_snapshots":[{"event_id":"sha256:09e345788511b028827bbefc344295405c5044aef8d792d89bea1824288d0497","target":"graph","created_at":"2026-07-05T11:43:29Z","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/2410.15956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Large Language Models (LLMs) are predominantly designed with English as the primary language, and even the few that are multilingual tend to exhibit strong English-centric biases. Much like speakers who might produce awkward expressions when learning a second language, LLMs often generate unnatural outputs in non-English languages, reflecting English-centric patterns in both vocabulary and grammar. Despite the importance of this issue, the naturalness of multilingual LLM outputs has received limited attention. In this paper, we address this gap by introducing novel automatic corpus-lev","authors_text":"Henry Xiao, Min Li, Saloni Potdar, Simone Conia, Yanzhu Guo, Zelin Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T12:34:17Z","title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15956","kind":"arxiv","version":3},"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":"sha256:33d5664a9cd3ac206c7fb0e0504b5f0a7436ff903ae2c46b59e6016c94bcd30a","target":"record","created_at":"2026-07-05T11:43:29Z","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":"b43c8df27e7e4874e50a09b133d947fa7c73b88210cc4623b580eaa22e996141","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T12:34:17Z","title_canon_sha256":"19d5bfdc940414c9f0798c33a9663586b728c7438600bdc7b1094593ada641d8"},"schema_version":"1.0","source":{"id":"2410.15956","kind":"arxiv","version":3}},"canonical_sha256":"d26a34b569efc046e010c38c4f5da2688af63ae59c634449b3504542b1220c34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d26a34b569efc046e010c38c4f5da2688af63ae59c634449b3504542b1220c34","first_computed_at":"2026-07-05T11:43:29.569500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:29.569500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wfbyQsf36iv16w+xLZ82itxeU2TbuS1S6p4+j/vNm2BBFrHMPHFBLg6eGkAJDKMPIm2WS5fSSYlnLnwEneKsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:29.570049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15956","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33d5664a9cd3ac206c7fb0e0504b5f0a7436ff903ae2c46b59e6016c94bcd30a","sha256:09e345788511b028827bbefc344295405c5044aef8d792d89bea1824288d0497"],"state_sha256":"c4442f2252a9ceee8b2c2bbbeee10edac1ae865e7d6ac704d5a8832f91a08d37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S+fKvOQt0/+9bXIxKzfuQiSyxw3slx6wHhOhz1mpIXRdA2kSNpufH8aGqZldYf3IWWjLGiS0X1l8gLxXmmxkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:23:59.317987Z","bundle_sha256":"3811427c9cf79a9d26669a8ca644c3204232ac59ea3e62ca954cb43a6dc19b05"}}