{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HE4YNDUP6TKX4YTPORKLJ34EC6","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":"1074f7747314411c968211a46bcd7347fd7bc87f987b92b9d5f0825343ff5716","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T16:49:52Z","title_canon_sha256":"4c2cce2ac33002d9a2f694632c84b72887e1b6c0b44153e4a8fad29ed91a310e"},"schema_version":"1.0","source":{"id":"2412.10893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10893","created_at":"2026-07-05T09:49:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10893v1","created_at":"2026-07-05T09:49:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10893","created_at":"2026-07-05T09:49:24Z"},{"alias_kind":"pith_short_12","alias_value":"HE4YNDUP6TKX","created_at":"2026-07-05T09:49:24Z"},{"alias_kind":"pith_short_16","alias_value":"HE4YNDUP6TKX4YTP","created_at":"2026-07-05T09:49:24Z"},{"alias_kind":"pith_short_8","alias_value":"HE4YNDUP","created_at":"2026-07-05T09:49:24Z"}],"graph_snapshots":[{"event_id":"sha256:9c9b7b9965f3a1a260a9911354403ec67fe5b91031ab1c73c83f3a87fdd7cea0","target":"graph","created_at":"2026-07-05T09:49:24Z","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/2412.10893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Anton Alexandrov, Ce Zhang, Dimitar I. Dimitrov, Kristina Toutanova, Martin Vechev, Veselin Raychev","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T16:49:52Z","title":"BgGPT 1.0: Extending English-centric LLMs to other languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10893","kind":"arxiv","version":1},"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:a81a41dc0eb149214c4d143af0a3a987ed24c19d47d579fb73c3d2a050379e73","target":"record","created_at":"2026-07-05T09:49:24Z","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":"1074f7747314411c968211a46bcd7347fd7bc87f987b92b9d5f0825343ff5716","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T16:49:52Z","title_canon_sha256":"4c2cce2ac33002d9a2f694632c84b72887e1b6c0b44153e4a8fad29ed91a310e"},"schema_version":"1.0","source":{"id":"2412.10893","kind":"arxiv","version":1}},"canonical_sha256":"3939868e8ff4d57e626f7454b4ef841794f33a2fbce1237f66f64e4cd891f97f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3939868e8ff4d57e626f7454b4ef841794f33a2fbce1237f66f64e4cd891f97f","first_computed_at":"2026-07-05T09:49:24.100301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:24.100301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d7reX2yRfCa580zRW+axy8dTKBBAO+X8bXUsC4/DmtqPnDBXbhFAG6Lan8c/AFyhIcx1m1IJwZd+Q9rPzEJzDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:24.100795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a81a41dc0eb149214c4d143af0a3a987ed24c19d47d579fb73c3d2a050379e73","sha256:9c9b7b9965f3a1a260a9911354403ec67fe5b91031ab1c73c83f3a87fdd7cea0"],"state_sha256":"89b56d8c6887a060fabb0890c70c8e48a2be40df71a854769e0b7ae7e46b344d"}