{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OL2LC2U2UIJL3JQ6OABBWDX5KD","short_pith_number":"pith:OL2LC2U2","canonical_record":{"source":{"id":"2311.05741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T20:59:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cfaabdfc53d9ca3afe806feef195fc1053d66cd81906731b94b6c1d4e80c41a4","abstract_canon_sha256":"1ffa52a54a5da75320aa0d8cb69f38f320f87edd59d5ea08e2b977a3821548e5"},"schema_version":"1.0"},"canonical_sha256":"72f4b16a9aa212bda61e70021b0efd50ea43bce3ff759df80ec68c6f89c45faa","source":{"kind":"arxiv","id":"2311.05741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05741","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05741v2","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05741","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"OL2LC2U2UIJL","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"OL2LC2U2UIJL3JQ6","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"OL2LC2U2","created_at":"2026-07-05T07:24:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OL2LC2U2UIJL3JQ6OABBWDX5KD","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T20:59:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cfaabdfc53d9ca3afe806feef195fc1053d66cd81906731b94b6c1d4e80c41a4","abstract_canon_sha256":"1ffa52a54a5da75320aa0d8cb69f38f320f87edd59d5ea08e2b977a3821548e5"},"schema_version":"1.0"},"canonical_sha256":"72f4b16a9aa212bda61e70021b0efd50ea43bce3ff759df80ec68c6f89c45faa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:21.280801Z","signature_b64":"a2mG126QTB9iuh1PFLokNOWrCzS4kxyAHWlYS2+x2eyqim1ogAcfeCGt+2qBUlQL4JRKjZuqJfPMhAXWNyzxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72f4b16a9aa212bda61e70021b0efd50ea43bce3ff759df80ec68c6f89c45faa","last_reissued_at":"2026-07-05T07:24:21.280343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:21.280343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05741","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HAvYRMSM1zL0qT4Psocwa65+LjcCdC64VRIy9CLlk65/ZwHtqJM72YSknkhfSbOz9akZ/JBHKn4BHejXVO5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:35:58.307967Z"},"content_sha256":"5e0f816399c4339ceec6db9509ed0869f555d8ad7d93425453b6e279ae6b3b0c","schema_version":"1.0","event_id":"sha256:5e0f816399c4339ceec6db9509ed0869f555d8ad7d93425453b6e279ae6b3b0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OL2LC2U2UIJL3JQ6OABBWDX5KD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Adapting Pretrained Language Models To New Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pian Pawakapan, Qiantong Xu, Urmish Thakker, Zoltan Csaki","submitted_at":"2023-11-09T20:59:08Z","abstract_excerpt":"Recent large language models (LLM) exhibit sub-optimal performance on low-resource languages, as the training data of these models is usually dominated by English and other high-resource languages. Furthermore, it is challenging to train models for low-resource languages, especially from scratch, due to a lack of high quality training data. Adapting pretrained LLMs reduces the need for data in the new language while also providing cross lingual transfer capabilities. However, naively adapting to new languages leads to catastrophic forgetting and poor tokenizer efficiency. In this work, we stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05741","kind":"arxiv","version":2},"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/2311.05741/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":"2026-07-05T07:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bAJkraqtLnqU6WUdvv0NuCjnBUz5gk7+S3Ld8ZnPf3vm0xUMdyHDUeiI6MTdOofs2eqP+PqiM9GT2u+ivKhcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:35:58.308351Z"},"content_sha256":"5351c7d548f7b89d3337cf33558afcf47a53ae6a2f51201e61ffa5398a8a690b","schema_version":"1.0","event_id":"sha256:5351c7d548f7b89d3337cf33558afcf47a53ae6a2f51201e61ffa5398a8a690b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD/bundle.json","state_url":"https://pith.science/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD/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":"2026-07-10T12:35:58Z","links":{"resolver":"https://pith.science/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD","bundle":"https://pith.science/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD/bundle.json","state":"https://pith.science/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OL2LC2U2UIJL3JQ6OABBWDX5KD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OL2LC2U2UIJL3JQ6OABBWDX5KD","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":"1ffa52a54a5da75320aa0d8cb69f38f320f87edd59d5ea08e2b977a3821548e5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T20:59:08Z","title_canon_sha256":"cfaabdfc53d9ca3afe806feef195fc1053d66cd81906731b94b6c1d4e80c41a4"},"schema_version":"1.0","source":{"id":"2311.05741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05741","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05741v2","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05741","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"OL2LC2U2UIJL","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"OL2LC2U2UIJL3JQ6","created_at":"2026-07-05T07:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"OL2LC2U2","created_at":"2026-07-05T07:24:21Z"}],"graph_snapshots":[{"event_id":"sha256:5351c7d548f7b89d3337cf33558afcf47a53ae6a2f51201e61ffa5398a8a690b","target":"graph","created_at":"2026-07-05T07:24:21Z","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/2311.05741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent large language models (LLM) exhibit sub-optimal performance on low-resource languages, as the training data of these models is usually dominated by English and other high-resource languages. Furthermore, it is challenging to train models for low-resource languages, especially from scratch, due to a lack of high quality training data. Adapting pretrained LLMs reduces the need for data in the new language while also providing cross lingual transfer capabilities. However, naively adapting to new languages leads to catastrophic forgetting and poor tokenizer efficiency. In this work, we stud","authors_text":"Pian Pawakapan, Qiantong Xu, Urmish Thakker, Zoltan Csaki","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T20:59:08Z","title":"Efficiently Adapting Pretrained Language Models To New Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05741","kind":"arxiv","version":2},"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":"sha256:5e0f816399c4339ceec6db9509ed0869f555d8ad7d93425453b6e279ae6b3b0c","target":"record","created_at":"2026-07-05T07:24:21Z","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":"1ffa52a54a5da75320aa0d8cb69f38f320f87edd59d5ea08e2b977a3821548e5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T20:59:08Z","title_canon_sha256":"cfaabdfc53d9ca3afe806feef195fc1053d66cd81906731b94b6c1d4e80c41a4"},"schema_version":"1.0","source":{"id":"2311.05741","kind":"arxiv","version":2}},"canonical_sha256":"72f4b16a9aa212bda61e70021b0efd50ea43bce3ff759df80ec68c6f89c45faa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72f4b16a9aa212bda61e70021b0efd50ea43bce3ff759df80ec68c6f89c45faa","first_computed_at":"2026-07-05T07:24:21.280343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:21.280343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a2mG126QTB9iuh1PFLokNOWrCzS4kxyAHWlYS2+x2eyqim1ogAcfeCGt+2qBUlQL4JRKjZuqJfPMhAXWNyzxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:21.280801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e0f816399c4339ceec6db9509ed0869f555d8ad7d93425453b6e279ae6b3b0c","sha256:5351c7d548f7b89d3337cf33558afcf47a53ae6a2f51201e61ffa5398a8a690b"],"state_sha256":"9e52d1ea2e7fcaef9135e631eddd86ebb01e63db90a0c4d67f8c731ce446e562"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kKlIJZx6dQyKEDn5FnStuNlNWfwo2aqRRdOs75tOeZgqZw53eUA9geMGU+A1QHf8hZQaA4phE+RlJmTlXMUcBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T12:35:58.310338Z","bundle_sha256":"40241fc0a29f76ecc99df4d8a96c4ffb4e13bd289f6c6c1e3b715958334c6c80"}}