{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IQYPIAGOG56J4W7YNRB7MNCJJL","short_pith_number":"pith:IQYPIAGO","schema_version":"1.0","canonical_sha256":"4430f400ce377c9e5bf86c43f634494ae45d292d5ad4b943ada8e99641774e86","source":{"kind":"arxiv","id":"2506.21566","version":1},"attestation_state":"computed","paper":{"title":"The Saturation Point of Backtranslation in High Quality Low Resource English Gujarati Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arwa Arif","submitted_at":"2025-06-12T09:02:53Z","abstract_excerpt":"Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness in high quality, low resource settings remains unclear. In this work, we explore the effectiveness of backtranslation for English Gujarati translation using the multilingual pretrained MBART50 model. Our baseline system, trained on a high quality parallel corpus of approximately 50,000 sentence pairs, achieves a BLEU score of 43.8 on a validation set. We aug"},"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":"2506.21566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T09:02:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"199fca091cb00998b10aef45eb50556e689f9892eda9baf40a20f52036b5ae49","abstract_canon_sha256":"4961228e00149f631c7d50e3dc1291089975d0c0d963504213ca23cb2cee3418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.477821Z","signature_b64":"C0DA6hfJ6fsc9DhgbcibABM0CaMhUrKQn8KQrC4P2XUk1Zc5sfNXNWX6oguPOZlej/z6+Lm81ubrAI9x1OoCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4430f400ce377c9e5bf86c43f634494ae45d292d5ad4b943ada8e99641774e86","last_reissued_at":"2026-07-05T11:27:56.477265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.477265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Saturation Point of Backtranslation in High Quality Low Resource English Gujarati Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arwa Arif","submitted_at":"2025-06-12T09:02:53Z","abstract_excerpt":"Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness in high quality, low resource settings remains unclear. In this work, we explore the effectiveness of backtranslation for English Gujarati translation using the multilingual pretrained MBART50 model. Our baseline system, trained on a high quality parallel corpus of approximately 50,000 sentence pairs, achieves a BLEU score of 43.8 on a validation set. We aug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21566","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/2506.21566/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":"2506.21566","created_at":"2026-07-05T11:27:56.477352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21566v1","created_at":"2026-07-05T11:27:56.477352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21566","created_at":"2026-07-05T11:27:56.477352+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQYPIAGOG56J","created_at":"2026-07-05T11:27:56.477352+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQYPIAGOG56J4W7Y","created_at":"2026-07-05T11:27:56.477352+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQYPIAGO","created_at":"2026-07-05T11:27:56.477352+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/IQYPIAGOG56J4W7YNRB7MNCJJL","json":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL.json","graph_json":"https://pith.science/api/pith-number/IQYPIAGOG56J4W7YNRB7MNCJJL/graph.json","events_json":"https://pith.science/api/pith-number/IQYPIAGOG56J4W7YNRB7MNCJJL/events.json","paper":"https://pith.science/paper/IQYPIAGO"},"agent_actions":{"view_html":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL","download_json":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL.json","view_paper":"https://pith.science/paper/IQYPIAGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21566&json=true","fetch_graph":"https://pith.science/api/pith-number/IQYPIAGOG56J4W7YNRB7MNCJJL/graph.json","fetch_events":"https://pith.science/api/pith-number/IQYPIAGOG56J4W7YNRB7MNCJJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL/action/storage_attestation","attest_author":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL/action/author_attestation","sign_citation":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL/action/citation_signature","submit_replication":"https://pith.science/pith/IQYPIAGOG56J4W7YNRB7MNCJJL/action/replication_record"}},"created_at":"2026-07-05T11:27:56.477352+00:00","updated_at":"2026-07-05T11:27:56.477352+00:00"}