{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WM4B4WWBN6NKFDFYJTMDCEZXLK","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":"a97426accf99f08c6914fdcab8a30122e30fc39392f0e3c462ba875142ac083f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T02:27:40Z","title_canon_sha256":"a49cd33cbc76f777a0d42a1997feca230c31ba5fe0d927b5f97048f64c4fa183"},"schema_version":"1.0","source":{"id":"2411.12986","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12986","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12986v2","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12986","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"pith_short_12","alias_value":"WM4B4WWBN6NK","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"pith_short_16","alias_value":"WM4B4WWBN6NKFDFY","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"pith_short_8","alias_value":"WM4B4WWB","created_at":"2026-07-05T10:10:09Z"}],"graph_snapshots":[{"event_id":"sha256:4166b3df0ec4274249bd0cfe179d239b6c1003587bc9cb22c20752ca0d6add9f","target":"graph","created_at":"2026-07-05T10:10:09Z","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/2411.12986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are trained on massive scrapes of the web, as required by current scaling laws. Most progress is made for English, given its abundance of high-quality pretraining data. For most other languages, however, such high quality pretraining data is unavailable. In this work, we study how to boost pretrained model performance in a target language with insufficient pretraining data for training a high performing language model, by enlisting data from an auxiliary language for which high quality data is available. We study this by quantifying the performance gap between training wi","authors_text":"David Grangier, Maartje ter Hoeve, Natalie Schluter, Richard He Bai, Skyler Seto","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T02:27:40Z","title":"Training Bilingual LMs with Data Constraints in the Targeted Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12986","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":"sha256:04305dfeb59b3137012ccbf05116963fdcd0314c2b7aab64fad28329e01ea6ad","target":"record","created_at":"2026-07-05T10:10:09Z","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":"a97426accf99f08c6914fdcab8a30122e30fc39392f0e3c462ba875142ac083f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T02:27:40Z","title_canon_sha256":"a49cd33cbc76f777a0d42a1997feca230c31ba5fe0d927b5f97048f64c4fa183"},"schema_version":"1.0","source":{"id":"2411.12986","kind":"arxiv","version":2}},"canonical_sha256":"b3381e5ac16f9aa28cb84cd83113375ab715969d6d9be532e20d7c9678960801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3381e5ac16f9aa28cb84cd83113375ab715969d6d9be532e20d7c9678960801","first_computed_at":"2026-07-05T10:10:09.814509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:09.814509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loBh4EjSIUjiSDs29ZeOlRQhOsQPEdbeUvxh1HJWE33pw/QJQvXBo6udOxT5afZXHBjrh6GNioBSKj2upuMhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:09.815065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12986","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04305dfeb59b3137012ccbf05116963fdcd0314c2b7aab64fad28329e01ea6ad","sha256:4166b3df0ec4274249bd0cfe179d239b6c1003587bc9cb22c20752ca0d6add9f"],"state_sha256":"74ad2687d00f77cc5090d89960a7351e3e70323949f8be27178f73e3a8b599fa"}