{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RAJXCWS2CJHRPYC3RCOY4LHBDG","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":"3eb0924efd9c3b1ad476541caac41b14684de01a5024858fb488fd4cfa495d70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T23:38:06Z","title_canon_sha256":"bd1cb8dbf21e9751552ad1a1cd5f9bbc4631777f0f80c5fc07d37dd846f87683"},"schema_version":"1.0","source":{"id":"2405.12413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12413","created_at":"2026-07-05T08:21:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12413v1","created_at":"2026-07-05T08:21:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12413","created_at":"2026-07-05T08:21:19Z"},{"alias_kind":"pith_short_12","alias_value":"RAJXCWS2CJHR","created_at":"2026-07-05T08:21:19Z"},{"alias_kind":"pith_short_16","alias_value":"RAJXCWS2CJHRPYC3","created_at":"2026-07-05T08:21:19Z"},{"alias_kind":"pith_short_8","alias_value":"RAJXCWS2","created_at":"2026-07-05T08:21:19Z"}],"graph_snapshots":[{"event_id":"sha256:44d507e556fec69a2489a82d39fd6c2a3e0317e3474edd0236fd491756a6fbdc","target":"graph","created_at":"2026-07-05T08:21:19Z","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/2405.12413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The \"massively-multilingual\" training of multilingual models is known to limit their utility in any one language, and they perform particularly poorly on low-resource languages. However, there is evidence that low-resource languages can benefit from targeted multilinguality, where the model is trained on closely related languages. To test this approach more rigorously, we systematically study best practices for adapting a pre-trained model to a language family. Focusing on the Uralic family as a test case, we adapt XLM-R under various configurations to model 15 languages; we then evaluate the ","authors_text":"C.M. Downey, Dhwani Serai, Dwija Parikh, Shane Steinert-Threlkeld, Terra Blevins","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T23:38:06Z","title":"Targeted Multilingual Adaptation for Low-resource Language Families"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12413","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":"sha256:7d790f52691c2ce9c7ad2f7fdcfcf9524e34337087538d992b47f26345edb9dc","target":"record","created_at":"2026-07-05T08:21:19Z","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":"3eb0924efd9c3b1ad476541caac41b14684de01a5024858fb488fd4cfa495d70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T23:38:06Z","title_canon_sha256":"bd1cb8dbf21e9751552ad1a1cd5f9bbc4631777f0f80c5fc07d37dd846f87683"},"schema_version":"1.0","source":{"id":"2405.12413","kind":"arxiv","version":1}},"canonical_sha256":"8813715a5a124f17e05b889d8e2ce119a413006d17173b632c63cf8be4d46580","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8813715a5a124f17e05b889d8e2ce119a413006d17173b632c63cf8be4d46580","first_computed_at":"2026-07-05T08:21:19.691059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:19.691059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W7vVgSPAqOpPcejJxtfZbBvDCm18PyoXOVJkE2DxF1vFlgPQ+nlHlCkopboskWLW3qAIRE6tsJgWsZj0ruRfCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:19.691530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d790f52691c2ce9c7ad2f7fdcfcf9524e34337087538d992b47f26345edb9dc","sha256:44d507e556fec69a2489a82d39fd6c2a3e0317e3474edd0236fd491756a6fbdc"],"state_sha256":"e4c200015d286c0e26788f77d35250b2700aa17216f2200e8cdbf60cd2a1a7c8"}