{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PPL2RADBK756WSEXRM5XVY2QXX","short_pith_number":"pith:PPL2RADB","schema_version":"1.0","canonical_sha256":"7bd7a8806157fbeb48978b3b7ae350bdcccfbddd640496d8ec22eafea31b810e","source":{"kind":"arxiv","id":"2405.04685","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Deniz Yuret, Emre Can Acikgoz, Mete Erdogan","submitted_at":"2024-05-07T21:58:45Z","abstract_excerpt":"Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations, with a special focus on Turkish. We conduct an in-depth analysis to evaluate the impact of training strategies, model choices, and data availability on the performance of LLMs designed for underrepresented languages. Our approach includes two methodologies: (i) adapting existing LLMs origi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.04685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T21:58:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c5ce73f5e1456daf2ded3bd29c342f0f8ffc8d5dd91041db7739d56fd7f59160","abstract_canon_sha256":"2f23ab3b31138acb4e5e3aeeaf395d865cf3e7841e93f2c502a7de3d3d06ea0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:52.496826Z","signature_b64":"USlH4F1S7jGKaFemHbXnBhOAzG6gUVzy7Md3vtP5t8tffvoi4QYaHb5UIb8kQrHdCmtd2F/TQ6nEABt1iDGiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd7a8806157fbeb48978b3b7ae350bdcccfbddd640496d8ec22eafea31b810e","last_reissued_at":"2026-07-05T08:16:52.496342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:52.496342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Deniz Yuret, Emre Can Acikgoz, Mete Erdogan","submitted_at":"2024-05-07T21:58:45Z","abstract_excerpt":"Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations, with a special focus on Turkish. We conduct an in-depth analysis to evaluate the impact of training strategies, model choices, and data availability on the performance of LLMs designed for underrepresented languages. Our approach includes two methodologies: (i) adapting existing LLMs origi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04685","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/2405.04685/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.04685","created_at":"2026-07-05T08:16:52.496402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04685v1","created_at":"2026-07-05T08:16:52.496402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04685","created_at":"2026-07-05T08:16:52.496402+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPL2RADBK756","created_at":"2026-07-05T08:16:52.496402+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPL2RADBK756WSEX","created_at":"2026-07-05T08:16:52.496402+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPL2RADB","created_at":"2026-07-05T08:16:52.496402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06202","citing_title":"Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX","json":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX.json","graph_json":"https://pith.science/api/pith-number/PPL2RADBK756WSEXRM5XVY2QXX/graph.json","events_json":"https://pith.science/api/pith-number/PPL2RADBK756WSEXRM5XVY2QXX/events.json","paper":"https://pith.science/paper/PPL2RADB"},"agent_actions":{"view_html":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX","download_json":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX.json","view_paper":"https://pith.science/paper/PPL2RADB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04685&json=true","fetch_graph":"https://pith.science/api/pith-number/PPL2RADBK756WSEXRM5XVY2QXX/graph.json","fetch_events":"https://pith.science/api/pith-number/PPL2RADBK756WSEXRM5XVY2QXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX/action/storage_attestation","attest_author":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX/action/author_attestation","sign_citation":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX/action/citation_signature","submit_replication":"https://pith.science/pith/PPL2RADBK756WSEXRM5XVY2QXX/action/replication_record"}},"created_at":"2026-07-05T08:16:52.496402+00:00","updated_at":"2026-07-05T08:16:52.496402+00:00"}