{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HE4YNDUP6TKX4YTPORKLJ34EC6","short_pith_number":"pith:HE4YNDUP","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"},"canonical_sha256":"3939868e8ff4d57e626f7454b4ef841794f33a2fbce1237f66f64e4cd891f97f","source":{"kind":"arxiv","id":"2412.10893","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HE4YNDUP6TKX4YTPORKLJ34EC6","target":"record","payload":{"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"},"canonical_sha256":"3939868e8ff4d57e626f7454b4ef841794f33a2fbce1237f66f64e4cd891f97f","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"},"source_kind":"arxiv","source_id":"2412.10893","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kqJMe6/x5lxeRbRLG3lO2Tgs/D9J6hUmNEi7EJIv+8n23+Um119T8ER5afpktzC94xPBcbgJSEw19OAAEvPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:16:07.563956Z"},"content_sha256":"a81a41dc0eb149214c4d143af0a3a987ed24c19d47d579fb73c3d2a050379e73","schema_version":"1.0","event_id":"sha256:a81a41dc0eb149214c4d143af0a3a987ed24c19d47d579fb73c3d2a050379e73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HE4YNDUP6TKX4YTPORKLJ34EC6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z05W3eA93o1OynRsafme4rnlzw07aoDO4CmDY1qbeCgwZAcq8uEqkDTcNnn9JuYHpRU92+0dzFpB2s5/s2B5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:16:07.564341Z"},"content_sha256":"9c9b7b9965f3a1a260a9911354403ec67fe5b91031ab1c73c83f3a87fdd7cea0","schema_version":"1.0","event_id":"sha256:9c9b7b9965f3a1a260a9911354403ec67fe5b91031ab1c73c83f3a87fdd7cea0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/bundle.json","state_url":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T16:16:07Z","links":{"resolver":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6","bundle":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/bundle.json","state":"https://pith.science/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HE4YNDUP6TKX4YTPORKLJ34EC6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qaGq+qpL+RykZS24dz0JNMA5MAdBuaWLkTT0/C96iV0Z9HzpBVzqPZFhqBZ0K9KOhXStohj0zRgaFc2oALPgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:16:07.566292Z","bundle_sha256":"a39504ea95500679fc5c1fbbcc6bb8534841db1f7d9bb8dee7f1e0012a812c12"}}