{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y3KD6K3MR64C3ZXL4WVTR3PW6V","short_pith_number":"pith:Y3KD6K3M","canonical_record":{"source":{"id":"2410.18836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T15:20:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"695c76d7a68fee84f53a156ed1210cb37a254f52b12cbe240079f3deb0ce1cff","abstract_canon_sha256":"6d8a88f87768642ee19f1d4f6a6656cebfd8aaeb13923bff9e3f57b66827f987"},"schema_version":"1.0"},"canonical_sha256":"c6d43f2b6c8fb82de6ebe5ab38edf6f56efb2421a0fe394de88ca4895de35a9f","source":{"kind":"arxiv","id":"2410.18836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18836","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18836v1","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18836","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"Y3KD6K3MR64C","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"Y3KD6K3MR64C3ZXL","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"Y3KD6K3M","created_at":"2026-07-05T09:25:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y3KD6K3MR64C3ZXL4WVTR3PW6V","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T15:20:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"695c76d7a68fee84f53a156ed1210cb37a254f52b12cbe240079f3deb0ce1cff","abstract_canon_sha256":"6d8a88f87768642ee19f1d4f6a6656cebfd8aaeb13923bff9e3f57b66827f987"},"schema_version":"1.0"},"canonical_sha256":"c6d43f2b6c8fb82de6ebe5ab38edf6f56efb2421a0fe394de88ca4895de35a9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:14.224385Z","signature_b64":"h3UuBpxtWhCj/MXFqSThs/iHK1hCJ+8GnRfssf4EH0cUHJoprNFRb7Bs7i8udS3jw6UEEG6WGGy+s1ujDPbqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d43f2b6c8fb82de6ebe5ab38edf6f56efb2421a0fe394de88ca4895de35a9f","last_reissued_at":"2026-07-05T09:25:14.223989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:14.223989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18836","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":"2026-07-05T09:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+s0aRu98cc5FLyetF/nVGyxfFF1YFO6NIJGaaGOfn15Alb1WD/+lgvzQDjWrKHDxrJ1O06KqMFAQYxyhtCPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:41:42.971797Z"},"content_sha256":"b97dcb7e0626a228fc7c85c885912ec672ba6ec49f32e7179beb9b7b10754374","schema_version":"1.0","event_id":"sha256:b97dcb7e0626a228fc7c85c885912ec672ba6ec49f32e7179beb9b7b10754374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y3KD6K3MR64C3ZXL4WVTR3PW6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anton Polishko, Artur Kiulian, Dmytro Chaplynskyi, Fadi Zaraket, Grigol Peradze, Guillermo Gabrielli, Hrishikesh Garud, {\\L}ukasz Gaga{\\l}a, Mykola Khandoga, Qusai Abu Obaida, Selma Belhadj Amor, Wendy Wing Yee Mak, Yevhen Kostiuk","submitted_at":"2024-10-24T15:20:54Z","abstract_excerpt":"In this paper, we propose a model-agnostic cost-effective approach to developing bilingual base large language models (LLMs) to support English and any target language. The method includes vocabulary expansion, initialization of new embeddings, model training and evaluation. We performed our experiments with three languages, each using a non-Latin script - Ukrainian, Arabic, and Georgian.\n  Our approach demonstrates improved language performance while reducing computational costs. It mitigates the disproportionate penalization of underrepresented languages, promoting fairness and minimizing ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18836","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/2410.18836/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":"2026-07-05T09:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PU1TsPFNFjj9qpxuDCD5C85NiMGMAaE7RvkrQaRlzR8+Ua4moFYvYXvKO7MN/msB5y+QpJp1LpBAR7CpaTDmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:41:42.972353Z"},"content_sha256":"4299aea5d0e4e9238468105bc2a260163f2f6b7d79001fe9622ac92cfacc82c5","schema_version":"1.0","event_id":"sha256:4299aea5d0e4e9238468105bc2a260163f2f6b7d79001fe9622ac92cfacc82c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V/bundle.json","state_url":"https://pith.science/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V/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":"2026-08-10T12:41:42Z","links":{"resolver":"https://pith.science/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V","bundle":"https://pith.science/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V/bundle.json","state":"https://pith.science/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3KD6K3MR64C3ZXL4WVTR3PW6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y3KD6K3MR64C3ZXL4WVTR3PW6V","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":"6d8a88f87768642ee19f1d4f6a6656cebfd8aaeb13923bff9e3f57b66827f987","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T15:20:54Z","title_canon_sha256":"695c76d7a68fee84f53a156ed1210cb37a254f52b12cbe240079f3deb0ce1cff"},"schema_version":"1.0","source":{"id":"2410.18836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18836","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18836v1","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18836","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"Y3KD6K3MR64C","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"Y3KD6K3MR64C3ZXL","created_at":"2026-07-05T09:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"Y3KD6K3M","created_at":"2026-07-05T09:25:14Z"}],"graph_snapshots":[{"event_id":"sha256:4299aea5d0e4e9238468105bc2a260163f2f6b7d79001fe9622ac92cfacc82c5","target":"graph","created_at":"2026-07-05T09:25:14Z","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/2410.18836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a model-agnostic cost-effective approach to developing bilingual base large language models (LLMs) to support English and any target language. The method includes vocabulary expansion, initialization of new embeddings, model training and evaluation. We performed our experiments with three languages, each using a non-Latin script - Ukrainian, Arabic, and Georgian.\n  Our approach demonstrates improved language performance while reducing computational costs. It mitigates the disproportionate penalization of underrepresented languages, promoting fairness and minimizing ad","authors_text":"Anton Polishko, Artur Kiulian, Dmytro Chaplynskyi, Fadi Zaraket, Grigol Peradze, Guillermo Gabrielli, Hrishikesh Garud, {\\L}ukasz Gaga{\\l}a, Mykola Khandoga, Qusai Abu Obaida, Selma Belhadj Amor, Wendy Wing Yee Mak, Yevhen Kostiuk","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T15:20:54Z","title":"From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18836","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:b97dcb7e0626a228fc7c85c885912ec672ba6ec49f32e7179beb9b7b10754374","target":"record","created_at":"2026-07-05T09:25:14Z","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":"6d8a88f87768642ee19f1d4f6a6656cebfd8aaeb13923bff9e3f57b66827f987","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T15:20:54Z","title_canon_sha256":"695c76d7a68fee84f53a156ed1210cb37a254f52b12cbe240079f3deb0ce1cff"},"schema_version":"1.0","source":{"id":"2410.18836","kind":"arxiv","version":1}},"canonical_sha256":"c6d43f2b6c8fb82de6ebe5ab38edf6f56efb2421a0fe394de88ca4895de35a9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6d43f2b6c8fb82de6ebe5ab38edf6f56efb2421a0fe394de88ca4895de35a9f","first_computed_at":"2026-07-05T09:25:14.223989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:14.223989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h3UuBpxtWhCj/MXFqSThs/iHK1hCJ+8GnRfssf4EH0cUHJoprNFRb7Bs7i8udS3jw6UEEG6WGGy+s1ujDPbqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:14.224385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b97dcb7e0626a228fc7c85c885912ec672ba6ec49f32e7179beb9b7b10754374","sha256:4299aea5d0e4e9238468105bc2a260163f2f6b7d79001fe9622ac92cfacc82c5"],"state_sha256":"2cfb6fa24123e4ae1dd5192ca4b4d89c44b7db1057463de17ed46300fe179285"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVsZ5Qh1f12jr3fgwuacbgVhGNnzQhAmOixHOW3vnq7gBKn0fcHm5EtqbF0KO6Rre4JyhwQ3Udcn4B8MQf5QAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:41:42.978884Z","bundle_sha256":"23840243400c5805ade2b7ca1edcc99ce6883fa08da70a7f572364ea7c0faa72"}}