{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z2O3Z3G4DQEX7JK7R2DUA35RA4","short_pith_number":"pith:Z2O3Z3G4","canonical_record":{"source":{"id":"2205.10517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T06:44:59Z","cross_cats_sorted":[],"title_canon_sha256":"975a49474f39dac76c1cfcfbe7f2f578984be25e92c5a6a9517b50346af38828","abstract_canon_sha256":"781cbf6ce8a69d16ad764804b2ce65ba062852f1e9f1a26fb139a6d41bf80c71"},"schema_version":"1.0"},"canonical_sha256":"ce9dbcecdc1c097fa55f8e87406fb107007fa9ea5330272056e444fed669798b","source":{"kind":"arxiv","id":"2205.10517","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z2O3Z3G4DQEX7JK7R2DUA35RA4","target":"record","payload":{"canonical_record":{"source":{"id":"2205.10517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T06:44:59Z","cross_cats_sorted":[],"title_canon_sha256":"975a49474f39dac76c1cfcfbe7f2f578984be25e92c5a6a9517b50346af38828","abstract_canon_sha256":"781cbf6ce8a69d16ad764804b2ce65ba062852f1e9f1a26fb139a6d41bf80c71"},"schema_version":"1.0"},"canonical_sha256":"ce9dbcecdc1c097fa55f8e87406fb107007fa9ea5330272056e444fed669798b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:37.799713Z","signature_b64":"g+sJdUJeRutXQXCyHJbzdOfmeYKXg1ve/V9m2RrSSZLO3alljom3WXWdzeKK4kUz8Zkywuz+0mGVYv7ZurMSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce9dbcecdc1c097fa55f8e87406fb107007fa9ea5330272056e444fed669798b","last_reissued_at":"2026-07-05T04:46:37.799267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:37.799267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.10517","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PYH4YYZEZWsFLiR4PzEYWlbmY9Peo7HIFtvTuNxNe1MhugPEbev5Xo8592IsxE9lqzsldri+h57ZcO4+V6r/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T05:33:21.503341Z"},"content_sha256":"4264be9cb9e1e1b2363ea8852fa065ce9fde16f77c62d62fff1e0eca40f2aa5d","schema_version":"1.0","event_id":"sha256:4264be9cb9e1e1b2363ea8852fa065ce9fde16f77c62d62fff1e0eca40f2aa5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z2O3Z3G4DQEX7JK7R2DUA35RA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Claudia Borg, Kurt Micallef, Lonneke van der Plas, Marc Tanti","submitted_at":"2022-05-21T06:44:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10517","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/2205.10517/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Z6475vLTDWgGisXDYGur0WDQ3ty3guoV7fnwvUBrZsiNyncYXC8xLXSzA2h+eplxhvJrMTA0K4Mu5IFhsxQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T05:33:21.503728Z"},"content_sha256":"f31868c1311fd8377f7762801ef6177076e18d09088c91727c020ab3937df692","schema_version":"1.0","event_id":"sha256:f31868c1311fd8377f7762801ef6177076e18d09088c91727c020ab3937df692"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4/bundle.json","state_url":"https://pith.science/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-20T05:33:21Z","links":{"resolver":"https://pith.science/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4","bundle":"https://pith.science/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4/bundle.json","state":"https://pith.science/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2O3Z3G4DQEX7JK7R2DUA35RA4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcXx38WV4Lqhtk7gVu9v9n3AJuHvCz6GG9TOTeEC/C+TG6/3FRSejEX67ilv9CFUUhnoVHWn0E7cR05o9hL2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T05:33:21.506131Z","bundle_sha256":"b4aae415274079aef391801cc59f3fb3a61563bd8a6f72a1891d4548271aaa83"}}