{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6LP47DHLU7QTXWTOIIWHKHDLMC","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":"93450a99ea084b47e03d65bbe3b594b284a432010fe118f06d8324326a7272e1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-09T15:04:32Z","title_canon_sha256":"b1f689613ca4ab14729f3becff49a32a187e6df04c6d6447049cedf754be0fcd"},"schema_version":"1.0","source":{"id":"2605.27379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27379","created_at":"2026-05-28T00:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27379v1","created_at":"2026-05-28T00:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27379","created_at":"2026-05-28T00:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"6LP47DHLU7QT","created_at":"2026-05-28T00:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"6LP47DHLU7QTXWTO","created_at":"2026-05-28T00:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"6LP47DHL","created_at":"2026-05-28T00:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:e530a969081b27c5a80a094a3653a936228134dbb82c9a66e2951b17f5060638","target":"graph","created_at":"2026-05-28T00:05:15Z","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/2605.27379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Azizjon Azimi, Bonu Boboeva, Haitz S\\'aez de Oc\\'ariz Borde, Khushbakht Shaymardonov, Shuhratjon Khalitbekov, Stanislav Liashkov","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-09T15:04:32Z","title":"Soro: A Lightweight Foundation Model and Chatbot for Tajik"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27379","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":"sha256:895bc9638cc39be9a13943c9deeef745e67704bf5592dcc8f710845a142308fa","target":"record","created_at":"2026-05-28T00:05:15Z","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":"93450a99ea084b47e03d65bbe3b594b284a432010fe118f06d8324326a7272e1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-09T15:04:32Z","title_canon_sha256":"b1f689613ca4ab14729f3becff49a32a187e6df04c6d6447049cedf754be0fcd"},"schema_version":"1.0","source":{"id":"2605.27379","kind":"arxiv","version":1}},"canonical_sha256":"f2dfcf8ceba7e13bda6e422c751c6b60bad1bfbc2351d2e9288f378e15e8b14c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2dfcf8ceba7e13bda6e422c751c6b60bad1bfbc2351d2e9288f378e15e8b14c","first_computed_at":"2026-05-28T00:05:15.909579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T00:05:15.909579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pkZr+KaXCTeqKAHD6gG4UrMWJzwo0ewidNo98lDfOX9sMHrC478xmwnhvELcUIG2zTlyoq3yQCiOtrjprY+0Dg==","signature_status":"signed_v1","signed_at":"2026-05-28T00:05:15.910350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:895bc9638cc39be9a13943c9deeef745e67704bf5592dcc8f710845a142308fa","sha256:e530a969081b27c5a80a094a3653a936228134dbb82c9a66e2951b17f5060638"],"state_sha256":"6675884952780f0fc5787bd5d48dfde40b74a8e55ab0df4b62b02e89dc316f35"}