{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FUECVDTUMHWEDPYUPTLQZ4FGBH","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":"bf1e5e3f7e8c55d838b2d94cac220ef14f6310b41a788c80e200e65e136ad2a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T16:32:28Z","title_canon_sha256":"e3a5bd3220949c8f329b8aaa4ca7b01c93d77731d8e9d99c61c2999933067b6b"},"schema_version":"1.0","source":{"id":"1907.00409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00409","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00409v1","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00409","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"pith_short_12","alias_value":"FUECVDTUMHWE","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FUECVDTUMHWEDPYU","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FUECVDTU","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:66514d0f272c291357bc6aecdbb4d1fde8555449cc1ebebfaa4b36630b47a0e6","target":"graph","created_at":"2026-05-17T23:41:36Z","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"},"paper":{"abstract_excerpt":"Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly. In this paper, we alleviate this scarcity problem for the low-resourced Filipino language in two ways. First, we introduce a new benchmark language modeling dataset in Filipino which we call WikiText-TL-39. Second, we show that language model finetuning techniques such as BERT and ULMFiT can be used to consistently train robust classifiers in low-resource settings, experienc","authors_text":"Charibeth Cheng, Jan Christian Blaise Cruz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T16:32:28Z","title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00409","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":"sha256:76ee65e1b7fdf3aeee04ad2741859a4a1f3a681413d92889f5f2d5f5fb41b946","target":"record","created_at":"2026-05-17T23:41:36Z","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":"bf1e5e3f7e8c55d838b2d94cac220ef14f6310b41a788c80e200e65e136ad2a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T16:32:28Z","title_canon_sha256":"e3a5bd3220949c8f329b8aaa4ca7b01c93d77731d8e9d99c61c2999933067b6b"},"schema_version":"1.0","source":{"id":"1907.00409","kind":"arxiv","version":1}},"canonical_sha256":"2d082a8e7461ec41bf147cd70cf0a609d79e2a127397b4e374ecbccc9114f611","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d082a8e7461ec41bf147cd70cf0a609d79e2a127397b4e374ecbccc9114f611","first_computed_at":"2026-05-17T23:41:36.089278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:36.089278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rwlSp1+ivvuH+6WYOWm6hfwWXiIISoAlrRTPUn/49M0Ur8uUfCN7CGV4aCAcgUEWOrsVyeLgSVv+nNLW4uCwCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:36.090060Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76ee65e1b7fdf3aeee04ad2741859a4a1f3a681413d92889f5f2d5f5fb41b946","sha256:66514d0f272c291357bc6aecdbb4d1fde8555449cc1ebebfaa4b36630b47a0e6"],"state_sha256":"011c013d2f5b7659cb1776ebca28ae68a2b74af15f349dc5e70821fd093e94b8"}