{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QPNPROMNUVFXV5Y6BDDVDXJT7Y","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":"76a58c610d7180cb4b2af2b146a1219929e6328fd9ff09c72eb119779420eade","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T22:56:56Z","title_canon_sha256":"dfceda292e0bae2b539be326c24231fcba1d9b6759e0e2c00f6dc03035fd86a0"},"schema_version":"1.0","source":{"id":"2402.02633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02633","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02633v1","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02633","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"QPNPROMNUVFX","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"QPNPROMNUVFXV5Y6","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"QPNPROMN","created_at":"2026-07-05T07:41:16Z"}],"graph_snapshots":[{"event_id":"sha256:925fc7dbfd4e39c974e1c80e74f1a12d538f7548490f64f39cc37f63c1d39d17","target":"graph","created_at":"2026-07-05T07:41:16Z","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/2402.02633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of natural language processing (NLP) tasks using machine learning methods, they primarily focus on high-resource languages, overlooking LRLs and shifts across domains. Focusing on LRLs, we investigate three factors: the size of the fine-tuning corpus, the domain similarity between fine-tuning and testing corpora, and the language similarity between source and target languages. We employ classical regression models to a","authors_text":"A. Seza Do\\u{g}ru\\\"oz, David Anugraha, En-Shiun Annie Lee, Eric Khiu, Hasti Toossi, Jiaxu Li, Jinyu Liu, Juan Armando Parra Flores, Leandro Acros Roman","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T22:56:56Z","title":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02633","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":"sha256:7b128751a932edf5aa285c11111d21728cc66bfca055078db7c075f0e65a7e30","target":"record","created_at":"2026-07-05T07:41:16Z","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":"76a58c610d7180cb4b2af2b146a1219929e6328fd9ff09c72eb119779420eade","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T22:56:56Z","title_canon_sha256":"dfceda292e0bae2b539be326c24231fcba1d9b6759e0e2c00f6dc03035fd86a0"},"schema_version":"1.0","source":{"id":"2402.02633","kind":"arxiv","version":1}},"canonical_sha256":"83daf8b98da54b7af71e08c751dd33fe0b0cae1da060e649ae8bd8d4d25eb8d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83daf8b98da54b7af71e08c751dd33fe0b0cae1da060e649ae8bd8d4d25eb8d9","first_computed_at":"2026-07-05T07:41:16.620809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:16.620809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Omt6Kfynk/SCIW92gho+vN8ttKVdScZXi/Rpck14/K09zoNIOuZlJ/sa3O3o/jr9pr+0VE0Y2LObAtcWN6sIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:16.621189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b128751a932edf5aa285c11111d21728cc66bfca055078db7c075f0e65a7e30","sha256:925fc7dbfd4e39c974e1c80e74f1a12d538f7548490f64f39cc37f63c1d39d17"],"state_sha256":"23879890abd2118799a62c8e8510b1df7435d9822c054fa39c2811d462332ca1"}