{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TU6F6LJ42IB5HZ3RS2YVGUUAHG","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":"822a0038fddfa8aeeb01c1de5e4a42ba1eeddef31ddc430c30a4ebeaae64414c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:29:08Z","title_canon_sha256":"97eb74246baf875b110231e128f73551771df55f0d8376824f7fa5f2242596a4"},"schema_version":"1.0","source":{"id":"2606.09767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09767","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09767v1","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09767","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"TU6F6LJ42IB5","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"TU6F6LJ42IB5HZ3R","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"TU6F6LJ4","created_at":"2026-06-09T02:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:b43435870b0b230384f58c6bf7186c73d70612b08749efcf0af6683bb20655d8","target":"graph","created_at":"2026-06-09T02:09:08Z","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/2606.09767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural machine translation for digitally low-resource Indigenous languages is often hindered by extreme data scarcity, prompting reliance on extractive web-scraping. To ensure data sovereignty, this study introduces a data synthesis methodology to bootstrap NMT models without scraping target-language parallel text. Focusing on Q'eqchi' Mayan, we transformed community-sourced dictionaries into a massive synthetic corpus, utilizing Parameter-Efficient Fine-Tuning (PEFT) via LoRA adapters on an mT5-base model.\n  In-domain evaluation demonstrates high structural acquisition (BLEU 42.02), proving t","authors_text":"Alexander Chulzhanov, Arjun Mukherjee, Soeren Eberhardt","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:29:08Z","title":"Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09767","kind":"arxiv","version":1},"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:ddec76bf28a0b2a291dca544960995a3391c81d77e082604f4c8a99397a263e3","target":"record","created_at":"2026-06-09T02:09:08Z","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":"822a0038fddfa8aeeb01c1de5e4a42ba1eeddef31ddc430c30a4ebeaae64414c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:29:08Z","title_canon_sha256":"97eb74246baf875b110231e128f73551771df55f0d8376824f7fa5f2242596a4"},"schema_version":"1.0","source":{"id":"2606.09767","kind":"arxiv","version":1}},"canonical_sha256":"9d3c5f2d3cd203d3e77196b153528039ac583a101b21ce8e71430f21d12157f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d3c5f2d3cd203d3e77196b153528039ac583a101b21ce8e71430f21d12157f7","first_computed_at":"2026-06-09T02:09:08.576786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:09:08.576786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jSdEk7/lnRRrPxzKdoCFM4BlpT2oMhqamsCFCEz3fJlZJEzMEYNbGQFZKFCMQFIiGLt12+qr/uZbt6pocQZwAg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:09:08.577525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddec76bf28a0b2a291dca544960995a3391c81d77e082604f4c8a99397a263e3","sha256:b43435870b0b230384f58c6bf7186c73d70612b08749efcf0af6683bb20655d8"],"state_sha256":"554048581712f0b337a761e25ef95ba48c6ddb96fce16198ab766ef993d56565"}