{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MPA3FYP6DJXWTNXC3GTE3WFV3R","short_pith_number":"pith:MPA3FYP6","canonical_record":{"source":{"id":"2605.15613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T04:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"6a657358a7a1ed9ce6296404faf86ab180240098beea380a075e7c529ac99c5c","abstract_canon_sha256":"4c45ebbe9c2b25112b3522a6ab96908087652fd653f999cd09280aa29409c1c9"},"schema_version":"1.0"},"canonical_sha256":"63c1b2e1fe1a6f69b6e2d9a64dd8b5dc7edb26c2eb0f378e2eb80ab34d4031a4","source":{"kind":"arxiv","id":"2605.15613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15613","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15613v1","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15613","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"pith_short_12","alias_value":"MPA3FYP6DJXW","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"pith_short_16","alias_value":"MPA3FYP6DJXWTNXC","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"pith_short_8","alias_value":"MPA3FYP6","created_at":"2026-05-20T00:01:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MPA3FYP6DJXWTNXC3GTE3WFV3R","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T04:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"6a657358a7a1ed9ce6296404faf86ab180240098beea380a075e7c529ac99c5c","abstract_canon_sha256":"4c45ebbe9c2b25112b3522a6ab96908087652fd653f999cd09280aa29409c1c9"},"schema_version":"1.0"},"canonical_sha256":"63c1b2e1fe1a6f69b6e2d9a64dd8b5dc7edb26c2eb0f378e2eb80ab34d4031a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:08.187428Z","signature_b64":"11O91tWOP/5DRRfMwRgPOow93swYLYs7yJt/6NVm4N/LLHryiRdV3e/X9pf3MvL4uJT1A0gj7KO16zHZYtuBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63c1b2e1fe1a6f69b6e2d9a64dd8b5dc7edb26c2eb0f378e2eb80ab34d4031a4","last_reissued_at":"2026-05-20T00:01:08.186591Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:08.186591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15613","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":"2026-05-20T00:01:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lhpuugb9DdyHRX3JYTy8Iw6u8TyLFZMNk8HAXCGi94mo/xSTJnqQDd6b9z/ZUMC3KdyTiPguxKK/BzQEEUCsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:06:40.887173Z"},"content_sha256":"9ac067eabc7ea49204e407fefc76866ea62125b38627983222c72e9dd5ffa317","schema_version":"1.0","event_id":"sha256:9ac067eabc7ea49204e407fefc76866ea62125b38627983222c72e9dd5ffa317"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MPA3FYP6DJXWTNXC3GTE3WFV3R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward LLMs Beyond English-Centric Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sho Takase, Ukyo Honda","submitted_at":"2026-05-15T04:51:07Z","abstract_excerpt":"Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15613","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/2605.15613/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.618770Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.043988Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d85762366345854aab75fbd42d04e6dba83c8ebf795391d575ee202ae1767312"},"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":"2026-05-20T00:01:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"doyqlFsdtUwNstvKvPSTC/2w4NPwfo1iuVNa6gVAdtyCZmHgAGT7ecnnrlCUuvFkbeqDGes1jTo36B8rjFELCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:06:40.887593Z"},"content_sha256":"dd5484165b38f62f37d561c2692b36643adc6bcfc32f3d381ad5b879d9a99a8f","schema_version":"1.0","event_id":"sha256:dd5484165b38f62f37d561c2692b36643adc6bcfc32f3d381ad5b879d9a99a8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R/bundle.json","state_url":"https://pith.science/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R/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":"2026-06-04T15:06:40Z","links":{"resolver":"https://pith.science/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R","bundle":"https://pith.science/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R/bundle.json","state":"https://pith.science/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPA3FYP6DJXWTNXC3GTE3WFV3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPA3FYP6DJXWTNXC3GTE3WFV3R","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":"4c45ebbe9c2b25112b3522a6ab96908087652fd653f999cd09280aa29409c1c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T04:51:07Z","title_canon_sha256":"6a657358a7a1ed9ce6296404faf86ab180240098beea380a075e7c529ac99c5c"},"schema_version":"1.0","source":{"id":"2605.15613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15613","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15613v1","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15613","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"pith_short_12","alias_value":"MPA3FYP6DJXW","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"pith_short_16","alias_value":"MPA3FYP6DJXWTNXC","created_at":"2026-05-20T00:01:08Z"},{"alias_kind":"pith_short_8","alias_value":"MPA3FYP6","created_at":"2026-05-20T00:01:08Z"}],"graph_snapshots":[{"event_id":"sha256:dd5484165b38f62f37d561c2692b36643adc6bcfc32f3d381ad5b879d9a99a8f","target":"graph","created_at":"2026-05-20T00:01:08Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.618770Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.043988Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15613/integrity.json","findings":[],"snapshot_sha256":"d85762366345854aab75fbd42d04e6dba83c8ebf795391d575ee202ae1767312","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.","authors_text":"Sho Takase, Ukyo Honda","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T04:51:07Z","title":"Toward LLMs Beyond English-Centric Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15613","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":"sha256:9ac067eabc7ea49204e407fefc76866ea62125b38627983222c72e9dd5ffa317","target":"record","created_at":"2026-05-20T00:01:08Z","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":"4c45ebbe9c2b25112b3522a6ab96908087652fd653f999cd09280aa29409c1c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T04:51:07Z","title_canon_sha256":"6a657358a7a1ed9ce6296404faf86ab180240098beea380a075e7c529ac99c5c"},"schema_version":"1.0","source":{"id":"2605.15613","kind":"arxiv","version":1}},"canonical_sha256":"63c1b2e1fe1a6f69b6e2d9a64dd8b5dc7edb26c2eb0f378e2eb80ab34d4031a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63c1b2e1fe1a6f69b6e2d9a64dd8b5dc7edb26c2eb0f378e2eb80ab34d4031a4","first_computed_at":"2026-05-20T00:01:08.186591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:08.186591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11O91tWOP/5DRRfMwRgPOow93swYLYs7yJt/6NVm4N/LLHryiRdV3e/X9pf3MvL4uJT1A0gj7KO16zHZYtuBCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:08.187428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ac067eabc7ea49204e407fefc76866ea62125b38627983222c72e9dd5ffa317","sha256:dd5484165b38f62f37d561c2692b36643adc6bcfc32f3d381ad5b879d9a99a8f"],"state_sha256":"6da5a6d6805b05b6a6d2980ab24f72f38fe0fe491af7b54d33a4506cd8d94c71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mA9mIz+Pfbg0XEhdhonjQwzmnfvCWHNW/WbSr3GyfHxrLs7RsIsDNPfo5PN1bEIApHLcol54Kw0Hgc5KKcVFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T15:06:40.889750Z","bundle_sha256":"4d3a15ca4d32adac01816bb16e3e8cb1c05fdf912bf05bc50cd3c3aa254c3472"}}