{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZ4QCQP7I6J2WNZIW3VUZJHTD5","short_pith_number":"pith:LZ4QCQP7","schema_version":"1.0","canonical_sha256":"5e790141ff4793ab3728b6eb4ca4f31f5dcb581391c30c9da245b685e3e8e3e6","source":{"kind":"arxiv","id":"2401.08429","version":1},"attestation_state":"computed","paper":{"title":"Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nooshin Pourkamali, Shler Ebrahim Sharifi","submitted_at":"2024-01-16T15:16:34Z","abstract_excerpt":"Generative large language models (LLMs) have demonstrated exceptional proficiency in various natural language processing (NLP) tasks, including machine translation, question answering, text summarization, and natural language understanding.\n  To further enhance the performance of LLMs in machine translation, we conducted an investigation into two popular prompting methods and their combination, focusing on cross-language combinations of Persian, English, and Russian. We employed n-shot feeding and tailored prompting frameworks. Our findings indicate that multilingual LLMs like PaLM exhibit hum"},"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":"2401.08429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T15:16:34Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"00a4a9ec90ce9ada23772ec1f9028b6f80531af884148381227d4178f88dc393","abstract_canon_sha256":"63ae1492a244a3d630b4d8270a366ae78737fbf7e6bac060e06cacb8c7f2d62a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:11.913934Z","signature_b64":"ArpqitL8CXGBACFTD3X9u+0LfeRnlXDLKDfnWNacoECfFxsDly+bPER1kQshlyIKz34+hAFb9ukp73c745zDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e790141ff4793ab3728b6eb4ca4f31f5dcb581391c30c9da245b685e3e8e3e6","last_reissued_at":"2026-07-05T07:34:11.913520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:11.913520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nooshin Pourkamali, Shler Ebrahim Sharifi","submitted_at":"2024-01-16T15:16:34Z","abstract_excerpt":"Generative large language models (LLMs) have demonstrated exceptional proficiency in various natural language processing (NLP) tasks, including machine translation, question answering, text summarization, and natural language understanding.\n  To further enhance the performance of LLMs in machine translation, we conducted an investigation into two popular prompting methods and their combination, focusing on cross-language combinations of Persian, English, and Russian. We employed n-shot feeding and tailored prompting frameworks. Our findings indicate that multilingual LLMs like PaLM exhibit hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08429","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/2401.08429/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":"2401.08429","created_at":"2026-07-05T07:34:11.913583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08429v1","created_at":"2026-07-05T07:34:11.913583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08429","created_at":"2026-07-05T07:34:11.913583+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZ4QCQP7I6J2","created_at":"2026-07-05T07:34:11.913583+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZ4QCQP7I6J2WNZI","created_at":"2026-07-05T07:34:11.913583+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZ4QCQP7","created_at":"2026-07-05T07:34:11.913583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06689","citing_title":"TAPO: Task-Referenced Adaptation for Prompt Optimization","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5","json":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5.json","graph_json":"https://pith.science/api/pith-number/LZ4QCQP7I6J2WNZIW3VUZJHTD5/graph.json","events_json":"https://pith.science/api/pith-number/LZ4QCQP7I6J2WNZIW3VUZJHTD5/events.json","paper":"https://pith.science/paper/LZ4QCQP7"},"agent_actions":{"view_html":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5","download_json":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5.json","view_paper":"https://pith.science/paper/LZ4QCQP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08429&json=true","fetch_graph":"https://pith.science/api/pith-number/LZ4QCQP7I6J2WNZIW3VUZJHTD5/graph.json","fetch_events":"https://pith.science/api/pith-number/LZ4QCQP7I6J2WNZIW3VUZJHTD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5/action/storage_attestation","attest_author":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5/action/author_attestation","sign_citation":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5/action/citation_signature","submit_replication":"https://pith.science/pith/LZ4QCQP7I6J2WNZIW3VUZJHTD5/action/replication_record"}},"created_at":"2026-07-05T07:34:11.913583+00:00","updated_at":"2026-07-05T07:34:11.913583+00:00"}