{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IRVVTVVDQV6CEYTCMO7CWVHPOH","short_pith_number":"pith:IRVVTVVD","schema_version":"1.0","canonical_sha256":"446b59d6a3857c22626263be2b54ef71ce3117ff35e96e73926f626a14ae4404","source":{"kind":"arxiv","id":"2404.17336","version":1},"attestation_state":"computed","paper":{"title":"Introducing cosmosGPT: Monolingual Training for Turkish Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Zeer, Atahan Uz, Eren Dogan, H. Emre Seyrek, H. Toprak Kesgin, M. Egemen Uzun, M. Fatih Amasyali, M. Kaan Yuce","submitted_at":"2024-04-26T11:34:11Z","abstract_excerpt":"The number of open source language models that can produce Turkish is increasing day by day, as in other languages. In order to create the basic versions of such models, the training of multilingual models is usually continued with Turkish corpora. The alternative is to train the model with only Turkish corpora. In this study, we first introduce the cosmosGPT models that we created with this alternative method. Then, we introduce new finetune datasets for basic language models to fulfill user requests and new evaluation datasets for measuring the capabilities of Turkish language models. Finall"},"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":"2404.17336","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:34:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ed10cff7af510414cc72adf21494f51259dc955f1a18f878334fcac505c8626","abstract_canon_sha256":"449acb76ced1c3189b093e3d29f692e8e1dd6e6964d714ea30aaf47edf17f6db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:36.375385Z","signature_b64":"oxc8aYlU+SUrj8RIFGMOVvTi9Kd41btyIPonPsb7asbl+25rrG1DmWQEVUOfafZ0IYyENU337P0W0sn66Tn1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446b59d6a3857c22626263be2b54ef71ce3117ff35e96e73926f626a14ae4404","last_reissued_at":"2026-07-05T08:12:36.374972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:36.374972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Introducing cosmosGPT: Monolingual Training for Turkish Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Zeer, Atahan Uz, Eren Dogan, H. Emre Seyrek, H. Toprak Kesgin, M. Egemen Uzun, M. Fatih Amasyali, M. Kaan Yuce","submitted_at":"2024-04-26T11:34:11Z","abstract_excerpt":"The number of open source language models that can produce Turkish is increasing day by day, as in other languages. In order to create the basic versions of such models, the training of multilingual models is usually continued with Turkish corpora. The alternative is to train the model with only Turkish corpora. In this study, we first introduce the cosmosGPT models that we created with this alternative method. Then, we introduce new finetune datasets for basic language models to fulfill user requests and new evaluation datasets for measuring the capabilities of Turkish language models. Finall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17336","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/2404.17336/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":"2404.17336","created_at":"2026-07-05T08:12:36.375029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17336v1","created_at":"2026-07-05T08:12:36.375029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17336","created_at":"2026-07-05T08:12:36.375029+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRVVTVVDQV6C","created_at":"2026-07-05T08:12:36.375029+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRVVTVVDQV6CEYTC","created_at":"2026-07-05T08:12:36.375029+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRVVTVVD","created_at":"2026-07-05T08:12:36.375029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02775","citing_title":"Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH","json":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH.json","graph_json":"https://pith.science/api/pith-number/IRVVTVVDQV6CEYTCMO7CWVHPOH/graph.json","events_json":"https://pith.science/api/pith-number/IRVVTVVDQV6CEYTCMO7CWVHPOH/events.json","paper":"https://pith.science/paper/IRVVTVVD"},"agent_actions":{"view_html":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH","download_json":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH.json","view_paper":"https://pith.science/paper/IRVVTVVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17336&json=true","fetch_graph":"https://pith.science/api/pith-number/IRVVTVVDQV6CEYTCMO7CWVHPOH/graph.json","fetch_events":"https://pith.science/api/pith-number/IRVVTVVDQV6CEYTCMO7CWVHPOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH/action/storage_attestation","attest_author":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH/action/author_attestation","sign_citation":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH/action/citation_signature","submit_replication":"https://pith.science/pith/IRVVTVVDQV6CEYTCMO7CWVHPOH/action/replication_record"}},"created_at":"2026-07-05T08:12:36.375029+00:00","updated_at":"2026-07-05T08:12:36.375029+00:00"}