{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z2O3Z3G4DQEX7JK7R2DUA35RA4","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":"781cbf6ce8a69d16ad764804b2ce65ba062852f1e9f1a26fb139a6d41bf80c71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T06:44:59Z","title_canon_sha256":"975a49474f39dac76c1cfcfbe7f2f578984be25e92c5a6a9517b50346af38828"},"schema_version":"1.0","source":{"id":"2205.10517","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10517","created_at":"2026-07-05T04:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10517v2","created_at":"2026-07-05T04:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10517","created_at":"2026-07-05T04:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"Z2O3Z3G4DQEX","created_at":"2026-07-05T04:46:37Z"},{"alias_kind":"pith_short_16","alias_value":"Z2O3Z3G4DQEX7JK7","created_at":"2026-07-05T04:46:37Z"},{"alias_kind":"pith_short_8","alias_value":"Z2O3Z3G4","created_at":"2026-07-05T04:46:37Z"}],"graph_snapshots":[{"event_id":"sha256:f31868c1311fd8377f7762801ef6177076e18d09088c91727c020ab3937df692","target":"graph","created_at":"2026-07-05T04:46:37Z","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/2205.10517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual language models such as mBERT have seen impressive cross-lingual transfer to a variety of languages, but many languages remain excluded from these models. In this paper, we analyse the effect of pre-training with monolingual data for a low-resource language that is not included in mBERT -- Maltese -- with a range of pre-training set ups. We conduct evaluations with the newly pre-trained models on three morphosyntactic tasks -- dependency parsing, part-of-speech tagging, and named-entity recognition -- and one semantic classification task -- sentiment analysis. We also present a ne","authors_text":"Albert Gatt, Claudia Borg, Kurt Micallef, Lonneke van der Plas, Marc Tanti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T06:44:59Z","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10517","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":"sha256:4264be9cb9e1e1b2363ea8852fa065ce9fde16f77c62d62fff1e0eca40f2aa5d","target":"record","created_at":"2026-07-05T04:46:37Z","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":"781cbf6ce8a69d16ad764804b2ce65ba062852f1e9f1a26fb139a6d41bf80c71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T06:44:59Z","title_canon_sha256":"975a49474f39dac76c1cfcfbe7f2f578984be25e92c5a6a9517b50346af38828"},"schema_version":"1.0","source":{"id":"2205.10517","kind":"arxiv","version":2}},"canonical_sha256":"ce9dbcecdc1c097fa55f8e87406fb107007fa9ea5330272056e444fed669798b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce9dbcecdc1c097fa55f8e87406fb107007fa9ea5330272056e444fed669798b","first_computed_at":"2026-07-05T04:46:37.799267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:37.799267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g+sJdUJeRutXQXCyHJbzdOfmeYKXg1ve/V9m2RrSSZLO3alljom3WXWdzeKK4kUz8Zkywuz+0mGVYv7ZurMSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:37.799713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10517","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4264be9cb9e1e1b2363ea8852fa065ce9fde16f77c62d62fff1e0eca40f2aa5d","sha256:f31868c1311fd8377f7762801ef6177076e18d09088c91727c020ab3937df692"],"state_sha256":"55e33c95eb8798219085dcaa3d48e3912cb6169c9a5af77a96ed6e4851c5a452"}