{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HE4YNDUP6TKX4YTPORKLJ34EC6","short_pith_number":"pith:HE4YNDUP","schema_version":"1.0","canonical_sha256":"3939868e8ff4d57e626f7454b4ef841794f33a2fbce1237f66f64e4cd891f97f","source":{"kind":"arxiv","id":"2412.10893","version":1},"attestation_state":"computed","paper":{"title":"BgGPT 1.0: Extending English-centric LLMs to other languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anton Alexandrov, Ce Zhang, Dimitar I. Dimitrov, Kristina Toutanova, Martin Vechev, Veselin Raychev","submitted_at":"2024-12-14T16:49:52Z","abstract_excerpt":"We present BgGPT-Gemma-2-27B-Instruct and BgGPT-Gemma-2-9B-Instruct: continually pretrained and fine-tuned versions of Google's Gemma-2 models, specifically optimized for Bulgarian language understanding and generation. Leveraging Gemma-2's multilingual capabilities and over 100 billion tokens of Bulgarian and English text data, our models demonstrate strong performance in Bulgarian language tasks, setting a new standard for language-specific AI models. Our approach maintains the robust capabilities of the original Gemma-2 models, ensuring that the English language performance remains intact. "},"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":"2412.10893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T16:49:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4c2cce2ac33002d9a2f694632c84b72887e1b6c0b44153e4a8fad29ed91a310e","abstract_canon_sha256":"1074f7747314411c968211a46bcd7347fd7bc87f987b92b9d5f0825343ff5716"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:24.100795Z","signature_b64":"d7reX2yRfCa580zRW+axy8dTKBBAO+X8bXUsC4/DmtqPnDBXbhFAG6Lan8c/AFyhIcx1m1IJwZd+Q9rPzEJzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3939868e8ff4d57e626f7454b4ef841794f33a2fbce1237f66f64e4cd891f97f","last_reissued_at":"2026-07-05T09:49:24.100301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:24.100301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BgGPT 1.0: Extending English-centric LLMs to other languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anton Alexandrov, Ce Zhang, Dimitar I. Dimitrov, Kristina Toutanova, Martin Vechev, Veselin Raychev","submitted_at":"2024-12-14T16:49:52Z","abstract_excerpt":"We present BgGPT-Gemma-2-27B-Instruct and BgGPT-Gemma-2-9B-Instruct: continually pretrained and fine-tuned versions of Google's Gemma-2 models, specifically optimized for Bulgarian language understanding and generation. Leveraging Gemma-2's multilingual capabilities and over 100 billion tokens of Bulgarian and English text data, our models demonstrate strong performance in Bulgarian language tasks, setting a new standard for language-specific AI models. Our approach maintains the robust capabilities of the original Gemma-2 models, ensuring that the English language performance remains intact. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10893","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/2412.10893/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":"2412.10893","created_at":"2026-07-05T09:49:24.100358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10893v1","created_at":"2026-07-05T09:49:24.100358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10893","created_at":"2026-07-05T09:49:24.100358+00:00"},{"alias_kind":"pith_short_12","alias_value":"HE4YNDUP6TKX","created_at":"2026-07-05T09:49:24.100358+00:00"},{"alias_kind":"pith_short_16","alias_value":"HE4YNDUP6TKX4YTP","created_at":"2026-07-05T09:49:24.100358+00:00"},{"alias_kind":"pith_short_8","alias_value":"HE4YNDUP","created_at":"2026-07-05T09:49:24.100358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11316","citing_title":"Sch\\\"utzen: Evaluating LLM Safety in Bulgarian and German Contexts","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6","json":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6.json","graph_json":"https://pith.science/api/pith-number/HE4YNDUP6TKX4YTPORKLJ34EC6/graph.json","events_json":"https://pith.science/api/pith-number/HE4YNDUP6TKX4YTPORKLJ34EC6/events.json","paper":"https://pith.science/paper/HE4YNDUP"},"agent_actions":{"view_html":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6","download_json":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6.json","view_paper":"https://pith.science/paper/HE4YNDUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10893&json=true","fetch_graph":"https://pith.science/api/pith-number/HE4YNDUP6TKX4YTPORKLJ34EC6/graph.json","fetch_events":"https://pith.science/api/pith-number/HE4YNDUP6TKX4YTPORKLJ34EC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/action/storage_attestation","attest_author":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/action/author_attestation","sign_citation":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/action/citation_signature","submit_replication":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/action/replication_record"}},"created_at":"2026-07-05T09:49:24.100358+00:00","updated_at":"2026-07-05T09:49:24.100358+00:00"}