{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CERWZGCKHOGMMPJRQI3ZITQYHY","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":"09479d1f63ff1ccf70f652398ec6e1647209b6ea639c8a3c450a3124d3b1d6ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-10T11:19:56Z","title_canon_sha256":"30459216f10980dac321353f94f2ac97f565c5a0503311ff2c992f7ee6e34dc4"},"schema_version":"1.0","source":{"id":"2205.04810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.04810","created_at":"2026-07-05T04:22:10Z"},{"alias_kind":"arxiv_version","alias_value":"2205.04810v1","created_at":"2026-07-05T04:22:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04810","created_at":"2026-07-05T04:22:10Z"},{"alias_kind":"pith_short_12","alias_value":"CERWZGCKHOGM","created_at":"2026-07-05T04:22:10Z"},{"alias_kind":"pith_short_16","alias_value":"CERWZGCKHOGMMPJR","created_at":"2026-07-05T04:22:10Z"},{"alias_kind":"pith_short_8","alias_value":"CERWZGCK","created_at":"2026-07-05T04:22:10Z"}],"graph_snapshots":[{"event_id":"sha256:2cbd955ef7b404c0a3112594a0ecf16ceb89ba2e92710e4b5d5a816b760ac449","target":"graph","created_at":"2026-07-05T04:22:10Z","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/2205.04810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available. We find that, in very low resource scenarios, statistical n-gram language models outperform state-of-the-art neural models. Our experiments show that this is mainly due to the focus of the former on a local context. As such, we introduce three methods to improve a neural model's performance in the low-resource setting, finding that limiting the model's self-attention is the most effective one, improving on downstream tasks such as NLI and POS tagging by up to 5% for the la","authors_text":"Antonio Toral, Gertjan van Noord, Lukas Edman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-10T11:19:56Z","title":"The Importance of Context in Very Low Resource Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04810","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:a3c02203e2914a2aa07fa23c911cab8589fb0ab5ffc19bb5d5822711aee4260c","target":"record","created_at":"2026-07-05T04:22:10Z","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":"09479d1f63ff1ccf70f652398ec6e1647209b6ea639c8a3c450a3124d3b1d6ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-10T11:19:56Z","title_canon_sha256":"30459216f10980dac321353f94f2ac97f565c5a0503311ff2c992f7ee6e34dc4"},"schema_version":"1.0","source":{"id":"2205.04810","kind":"arxiv","version":1}},"canonical_sha256":"11236c984a3b8cc63d318237944e183e2a943b48733299da8513219b6125fde0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11236c984a3b8cc63d318237944e183e2a943b48733299da8513219b6125fde0","first_computed_at":"2026-07-05T04:22:10.819364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:10.819364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j90SdB+hBv7FcIL6TnSiHAgAA+g78+YFtyH9nQgHJkmcSPmkfe/dgkkjrq7fiyUPcJ+59pbfenHZ2e25IqyyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:10.819849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.04810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3c02203e2914a2aa07fa23c911cab8589fb0ab5ffc19bb5d5822711aee4260c","sha256:2cbd955ef7b404c0a3112594a0ecf16ceb89ba2e92710e4b5d5a816b760ac449"],"state_sha256":"ea8ded354797234f790ec6ff7794b643bdffb6f069827d42b4e453f062f93d1d"}