{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q5FOC4DZKSEGDQOYW54ZVO3R6W","short_pith_number":"pith:Q5FOC4DZ","schema_version":"1.0","canonical_sha256":"874ae17079548861c1d8b7799abb71f5a09b361dd5a2e6c8772f0fb6f00b3cf1","source":{"kind":"arxiv","id":"2601.03135","version":2},"attestation_state":"computed","paper":{"title":"Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aashish Dhawan, Christan Grant, Christopher Driggers-Ellis, Daisy Zhe Wang","submitted_at":"2026-01-06T16:06:42Z","abstract_excerpt":"Low-resource indigenous languages often lack the parallel corpora required for effective neural machine translation (NMT). Synthetic data generation offers a practical strategy for mitigating this limitation in data-scarce settings. In this work, we augment curated parallel datasets for indigenous languages of the Americas with synthetic sentence pairs generated using a high-capacity multilingual translation model. We fine-tune a multilingual mBART model on curated-only and synthetically augmented data and evaluate translation quality using chrF++, the primary metric used in recent AmericasNLP"},"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":"2601.03135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T16:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"bd83103336d96d8724362abb547505fa6a968a51b6ef4d544a504feaf2dba3fa","abstract_canon_sha256":"23cc41eec74de978b4c03785198892a881954cb278b393fb114b22ff570a6dc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:20.434127Z","signature_b64":"PRhJqXciL3yeqvY4WybMDkPlzjmDZeHhswmqAb437oRsOdedDHoVSgcDgVc5YhsWPXGOBROSrcmWS9SnSNgCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874ae17079548861c1d8b7799abb71f5a09b361dd5a2e6c8772f0fb6f00b3cf1","last_reissued_at":"2026-05-21T01:04:20.433283Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:20.433283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aashish Dhawan, Christan Grant, Christopher Driggers-Ellis, Daisy Zhe Wang","submitted_at":"2026-01-06T16:06:42Z","abstract_excerpt":"Low-resource indigenous languages often lack the parallel corpora required for effective neural machine translation (NMT). Synthetic data generation offers a practical strategy for mitigating this limitation in data-scarce settings. In this work, we augment curated parallel datasets for indigenous languages of the Americas with synthetic sentence pairs generated using a high-capacity multilingual translation model. We fine-tune a multilingual mBART model on curated-only and synthetically augmented data and evaluate translation quality using chrF++, the primary metric used in recent AmericasNLP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03135","kind":"arxiv","version":2},"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/2601.03135/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":"2601.03135","created_at":"2026-05-21T01:04:20.433398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.03135v2","created_at":"2026-05-21T01:04:20.433398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03135","created_at":"2026-05-21T01:04:20.433398+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5FOC4DZKSEG","created_at":"2026-05-21T01:04:20.433398+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5FOC4DZKSEGDQOY","created_at":"2026-05-21T01:04:20.433398+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5FOC4DZ","created_at":"2026-05-21T01:04:20.433398+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/Q5FOC4DZKSEGDQOYW54ZVO3R6W","json":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W.json","graph_json":"https://pith.science/api/pith-number/Q5FOC4DZKSEGDQOYW54ZVO3R6W/graph.json","events_json":"https://pith.science/api/pith-number/Q5FOC4DZKSEGDQOYW54ZVO3R6W/events.json","paper":"https://pith.science/paper/Q5FOC4DZ"},"agent_actions":{"view_html":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W","download_json":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W.json","view_paper":"https://pith.science/paper/Q5FOC4DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.03135&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5FOC4DZKSEGDQOYW54ZVO3R6W/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5FOC4DZKSEGDQOYW54ZVO3R6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W/action/storage_attestation","attest_author":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W/action/author_attestation","sign_citation":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W/action/citation_signature","submit_replication":"https://pith.science/pith/Q5FOC4DZKSEGDQOYW54ZVO3R6W/action/replication_record"}},"created_at":"2026-05-21T01:04:20.433398+00:00","updated_at":"2026-05-21T01:04:20.433398+00:00"}