{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6LP47DHLU7QTXWTOIIWHKHDLMC","short_pith_number":"pith:6LP47DHL","schema_version":"1.0","canonical_sha256":"f2dfcf8ceba7e13bda6e422c751c6b60bad1bfbc2351d2e9288f378e15e8b14c","source":{"kind":"arxiv","id":"2605.27379","version":1},"attestation_state":"computed","paper":{"title":"Soro: A Lightweight Foundation Model and Chatbot for Tajik","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Azizjon Azimi, Bonu Boboeva, Haitz S\\'aez de Oc\\'ariz Borde, Khushbakht Shaymardonov, Shuhratjon Khalitbekov, Stanislav Liashkov","submitted_at":"2026-04-09T15:04:32Z","abstract_excerpt":"We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan. Starting from open-weight Gemma 3 checkpoints, we perform Tajik-only continual pretraining on a curated 1.9-billion-token corpus spanning filtered web text, PDF documents, and curriculum-aligned educational materials, followed by supervised instruction tuning on 40K Tajik teacher-style examples. To enable rigorous evaluation despite the limited coverage of Tajik in standard benchmarks, we introduce a suite "},"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":"2605.27379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-09T15:04:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b1f689613ca4ab14729f3becff49a32a187e6df04c6d6447049cedf754be0fcd","abstract_canon_sha256":"93450a99ea084b47e03d65bbe3b594b284a432010fe118f06d8324326a7272e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T00:05:15.910350Z","signature_b64":"pkZr+KaXCTeqKAHD6gG4UrMWJzwo0ewidNo98lDfOX9sMHrC478xmwnhvELcUIG2zTlyoq3yQCiOtrjprY+0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2dfcf8ceba7e13bda6e422c751c6b60bad1bfbc2351d2e9288f378e15e8b14c","last_reissued_at":"2026-05-28T00:05:15.909579Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T00:05:15.909579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soro: A Lightweight Foundation Model and Chatbot for Tajik","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Azizjon Azimi, Bonu Boboeva, Haitz S\\'aez de Oc\\'ariz Borde, Khushbakht Shaymardonov, Shuhratjon Khalitbekov, Stanislav Liashkov","submitted_at":"2026-04-09T15:04:32Z","abstract_excerpt":"We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan. Starting from open-weight Gemma 3 checkpoints, we perform Tajik-only continual pretraining on a curated 1.9-billion-token corpus spanning filtered web text, PDF documents, and curriculum-aligned educational materials, followed by supervised instruction tuning on 40K Tajik teacher-style examples. To enable rigorous evaluation despite the limited coverage of Tajik in standard benchmarks, we introduce a suite "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27379","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/2605.27379/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":"2605.27379","created_at":"2026-05-28T00:05:15.909687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27379v1","created_at":"2026-05-28T00:05:15.909687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27379","created_at":"2026-05-28T00:05:15.909687+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LP47DHLU7QT","created_at":"2026-05-28T00:05:15.909687+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LP47DHLU7QTXWTO","created_at":"2026-05-28T00:05:15.909687+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LP47DHL","created_at":"2026-05-28T00:05:15.909687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC","json":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC.json","graph_json":"https://pith.science/api/pith-number/6LP47DHLU7QTXWTOIIWHKHDLMC/graph.json","events_json":"https://pith.science/api/pith-number/6LP47DHLU7QTXWTOIIWHKHDLMC/events.json","paper":"https://pith.science/paper/6LP47DHL"},"agent_actions":{"view_html":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC","download_json":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC.json","view_paper":"https://pith.science/paper/6LP47DHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27379&json=true","fetch_graph":"https://pith.science/api/pith-number/6LP47DHLU7QTXWTOIIWHKHDLMC/graph.json","fetch_events":"https://pith.science/api/pith-number/6LP47DHLU7QTXWTOIIWHKHDLMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC/action/storage_attestation","attest_author":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC/action/author_attestation","sign_citation":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC/action/citation_signature","submit_replication":"https://pith.science/pith/6LP47DHLU7QTXWTOIIWHKHDLMC/action/replication_record"}},"created_at":"2026-05-28T00:05:15.909687+00:00","updated_at":"2026-05-28T00:05:15.909687+00:00"}