{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q5FOC4DZKSEGDQOYW54ZVO3R6W","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":"23cc41eec74de978b4c03785198892a881954cb278b393fb114b22ff570a6dc0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T16:06:42Z","title_canon_sha256":"bd83103336d96d8724362abb547505fa6a968a51b6ef4d544a504feaf2dba3fa"},"schema_version":"1.0","source":{"id":"2601.03135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.03135","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2601.03135v2","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03135","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"Q5FOC4DZKSEG","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"Q5FOC4DZKSEGDQOY","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"Q5FOC4DZ","created_at":"2026-05-21T01:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:53a5ca85afc9df1c68367c6e1e1b4f21a080f802f64825fa7b666eac94a6b368","target":"graph","created_at":"2026-05-21T01:04:20Z","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/2601.03135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aashish Dhawan, Christan Grant, Christopher Driggers-Ellis, Daisy Zhe Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T16:06:42Z","title":"Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03135","kind":"arxiv","version":2},"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":"sha256:68d272013fe9d59e7df6aaae88350fddc159f88f132dac58ad37064f7e37e0af","target":"record","created_at":"2026-05-21T01:04:20Z","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":"23cc41eec74de978b4c03785198892a881954cb278b393fb114b22ff570a6dc0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T16:06:42Z","title_canon_sha256":"bd83103336d96d8724362abb547505fa6a968a51b6ef4d544a504feaf2dba3fa"},"schema_version":"1.0","source":{"id":"2601.03135","kind":"arxiv","version":2}},"canonical_sha256":"874ae17079548861c1d8b7799abb71f5a09b361dd5a2e6c8772f0fb6f00b3cf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"874ae17079548861c1d8b7799abb71f5a09b361dd5a2e6c8772f0fb6f00b3cf1","first_computed_at":"2026-05-21T01:04:20.433283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:20.433283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PRhJqXciL3yeqvY4WybMDkPlzjmDZeHhswmqAb437oRsOdedDHoVSgcDgVc5YhsWPXGOBROSrcmWS9SnSNgCDQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:20.434127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.03135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68d272013fe9d59e7df6aaae88350fddc159f88f132dac58ad37064f7e37e0af","sha256:53a5ca85afc9df1c68367c6e1e1b4f21a080f802f64825fa7b666eac94a6b368"],"state_sha256":"a44e8b8e1e352379f60e0af6db60532b19ffffb64b5909427a2eb2b822965fc1"}