{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZMQTPXDVEHJJMFUFDL6IH4COC","short_pith_number":"pith:DZMQTPXD","schema_version":"1.0","canonical_sha256":"1e5909bee3a90e94b0b428d7e41f8270a77621f8e7ac698d38c679dea2d6541b","source":{"kind":"arxiv","id":"2412.21140","version":1},"attestation_state":"computed","paper":{"title":"Facilitating large language model Russian adaptation with Learned Embedding Propagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniil Chernyshev, Mikhail Tikhomirov","submitted_at":"2024-12-30T18:15:45Z","abstract_excerpt":"Rapid advancements of large language model (LLM) technologies led to the introduction of powerful open-source instruction-tuned LLMs that have the same text generation quality as the state-of-the-art counterparts such as GPT-4. While the emergence of such models accelerates the adoption of LLM technologies in sensitive-information environments the authors of such models don not disclose the training data necessary for replication of the results thus making the achievements model-exclusive. Since those open-source models are also multilingual this in turn reduces the benefits of training a lang"},"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":"2412.21140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T18:15:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"672ed2d59080ab4a077307cc79c597544805d00639e3340a640a68358ed7b059","abstract_canon_sha256":"3c7ac68eb157ac6510a83bc50adc42845e510eee14852c956007725f71e8484a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:27.718981Z","signature_b64":"lt9TaJ0lTudr3bV6D7SZFcsqWsFdgAQwqNpR7hNv4tz0ZE7KcLkoz6YrKY6flbg37CgvjJIRc+iUfl5jp5oPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e5909bee3a90e94b0b428d7e41f8270a77621f8e7ac698d38c679dea2d6541b","last_reissued_at":"2026-07-05T09:55:27.718474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:27.718474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Facilitating large language model Russian adaptation with Learned Embedding Propagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniil Chernyshev, Mikhail Tikhomirov","submitted_at":"2024-12-30T18:15:45Z","abstract_excerpt":"Rapid advancements of large language model (LLM) technologies led to the introduction of powerful open-source instruction-tuned LLMs that have the same text generation quality as the state-of-the-art counterparts such as GPT-4. While the emergence of such models accelerates the adoption of LLM technologies in sensitive-information environments the authors of such models don not disclose the training data necessary for replication of the results thus making the achievements model-exclusive. Since those open-source models are also multilingual this in turn reduces the benefits of training a lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.21140","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/2412.21140/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":"2412.21140","created_at":"2026-07-05T09:55:27.718538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.21140v1","created_at":"2026-07-05T09:55:27.718538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.21140","created_at":"2026-07-05T09:55:27.718538+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZMQTPXDVEHJ","created_at":"2026-07-05T09:55:27.718538+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZMQTPXDVEHJJMFU","created_at":"2026-07-05T09:55:27.718538+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZMQTPXD","created_at":"2026-07-05T09:55:27.718538+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/DZMQTPXDVEHJJMFUFDL6IH4COC","json":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC.json","graph_json":"https://pith.science/api/pith-number/DZMQTPXDVEHJJMFUFDL6IH4COC/graph.json","events_json":"https://pith.science/api/pith-number/DZMQTPXDVEHJJMFUFDL6IH4COC/events.json","paper":"https://pith.science/paper/DZMQTPXD"},"agent_actions":{"view_html":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC","download_json":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC.json","view_paper":"https://pith.science/paper/DZMQTPXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.21140&json=true","fetch_graph":"https://pith.science/api/pith-number/DZMQTPXDVEHJJMFUFDL6IH4COC/graph.json","fetch_events":"https://pith.science/api/pith-number/DZMQTPXDVEHJJMFUFDL6IH4COC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC/action/storage_attestation","attest_author":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC/action/author_attestation","sign_citation":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC/action/citation_signature","submit_replication":"https://pith.science/pith/DZMQTPXDVEHJJMFUFDL6IH4COC/action/replication_record"}},"created_at":"2026-07-05T09:55:27.718538+00:00","updated_at":"2026-07-05T09:55:27.718538+00:00"}