{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RVEYA5PVPC57SKDFUN4SRMGCNK","short_pith_number":"pith:RVEYA5PV","schema_version":"1.0","canonical_sha256":"8d498075f578bbf92865a37928b0c26aa229b11da42a85f31c906a12851c293d","source":{"kind":"arxiv","id":"2406.18266","version":4},"attestation_state":"computed","paper":{"title":"\"Vorbe\\c{s}ti Rom\\^ane\\c{s}te?\" A Recipe to Train Powerful Romanian LLMs with English Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandru Dima, Andrei Terian, Denis C. Ilie-Ablachim, Dragos Corlatescu, Horia Velicu, Marius Leordeanu, Marius Popescu, Mihai Dascalu, Mihai Masala, Miruna Zavelca, Ovio Olaru, Simina Terian, Traian Rebedea","submitted_at":"2024-06-26T11:39:51Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English; hence, their performance in English greatly exceeds other languages. To our knowledge, we are the first to collect and translate a large collection of texts, instructions, and benchmarks and train, evaluate, and release open-source LLMs tailored for Romanian. We evaluate our methods on four different categories, including academic benchmarks, MT-Bench (manually translated), and a professional"},"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":"2406.18266","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T11:39:51Z","cross_cats_sorted":[],"title_canon_sha256":"74abb299f430682a798aa9cac5ca6f97f6ab2e6f0c3bd380d45cccb60e982cbb","abstract_canon_sha256":"26e7c18f788b067f5717661627965554dfe97c4b53a8c8a70772cc24f76afa43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:59.419308Z","signature_b64":"bB4O1kD9yJEcT+uwRj61U9o5z5iiphUVOVMNKIev+pAs7UqxiwEZ0hxeZYns9XzZkP1axVETMYip8z2Q7pLPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d498075f578bbf92865a37928b0c26aa229b11da42a85f31c906a12851c293d","last_reissued_at":"2026-07-05T09:24:59.418824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:59.418824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Vorbe\\c{s}ti Rom\\^ane\\c{s}te?\" A Recipe to Train Powerful Romanian LLMs with English Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandru Dima, Andrei Terian, Denis C. Ilie-Ablachim, Dragos Corlatescu, Horia Velicu, Marius Leordeanu, Marius Popescu, Mihai Dascalu, Mihai Masala, Miruna Zavelca, Ovio Olaru, Simina Terian, Traian Rebedea","submitted_at":"2024-06-26T11:39:51Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English; hence, their performance in English greatly exceeds other languages. To our knowledge, we are the first to collect and translate a large collection of texts, instructions, and benchmarks and train, evaluate, and release open-source LLMs tailored for Romanian. We evaluate our methods on four different categories, including academic benchmarks, MT-Bench (manually translated), and a professional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18266","kind":"arxiv","version":4},"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/2406.18266/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":"2406.18266","created_at":"2026-07-05T09:24:59.418880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18266v4","created_at":"2026-07-05T09:24:59.418880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18266","created_at":"2026-07-05T09:24:59.418880+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVEYA5PVPC57","created_at":"2026-07-05T09:24:59.418880+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVEYA5PVPC57SKDF","created_at":"2026-07-05T09:24:59.418880+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVEYA5PV","created_at":"2026-07-05T09:24:59.418880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09701","citing_title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK","json":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK.json","graph_json":"https://pith.science/api/pith-number/RVEYA5PVPC57SKDFUN4SRMGCNK/graph.json","events_json":"https://pith.science/api/pith-number/RVEYA5PVPC57SKDFUN4SRMGCNK/events.json","paper":"https://pith.science/paper/RVEYA5PV"},"agent_actions":{"view_html":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK","download_json":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK.json","view_paper":"https://pith.science/paper/RVEYA5PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18266&json=true","fetch_graph":"https://pith.science/api/pith-number/RVEYA5PVPC57SKDFUN4SRMGCNK/graph.json","fetch_events":"https://pith.science/api/pith-number/RVEYA5PVPC57SKDFUN4SRMGCNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK/action/storage_attestation","attest_author":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK/action/author_attestation","sign_citation":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK/action/citation_signature","submit_replication":"https://pith.science/pith/RVEYA5PVPC57SKDFUN4SRMGCNK/action/replication_record"}},"created_at":"2026-07-05T09:24:59.418880+00:00","updated_at":"2026-07-05T09:24:59.418880+00:00"}