{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XYTTGTQNJZNK7N2J4UNUE6X5QK","short_pith_number":"pith:XYTTGTQN","schema_version":"1.0","canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","source":{"kind":"arxiv","id":"2302.07912","version":1},"attestation_state":"computed","paper":{"title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abteen Ebrahimi, Arturo Oncevay, Arya D. McCarthy, Gustavo A. Gim\\'enez-Lugo, John E. Ortega, Katharina Kann, Luis Chiruzzo, Rolando Coto-Solano","submitted_at":"2023-02-15T19:06:17Z","abstract_excerpt":"Large multilingual models have inspired a new class of word alignment methods, which work well for the model's pretraining languages. However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data. In this work, we ask: How do modern aligners perform on unseen languages, and are they better than traditional methods? We contribute gold-standard alignments for Bribri--Spanish, Guarani--Spanish, Quechua--Spanish, and Shipibo-Konibo--Spanish. With these, we evaluate state-of-the-art aligners with and without model adaptation to"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.07912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T19:06:17Z","cross_cats_sorted":[],"title_canon_sha256":"b04ecf59796efd1385b21baa09a8a7f5370ddd6008e96d60a6095856cbb1238b","abstract_canon_sha256":"4ed3c5a2f758ceea07c6b680a93943db866ed757218b8ce12153f345bd0e5792"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:31.804760Z","signature_b64":"W7RaYw9URiGk6vEw0rCkRzy3zpL15YSLsgtUL/vLyhWtvNAmUyDlPzFX0t7ud599LVtX9Gk3tqq58IyeUHXFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","last_reissued_at":"2026-07-05T05:42:31.804282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:31.804282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abteen Ebrahimi, Arturo Oncevay, Arya D. McCarthy, Gustavo A. Gim\\'enez-Lugo, John E. Ortega, Katharina Kann, Luis Chiruzzo, Rolando Coto-Solano","submitted_at":"2023-02-15T19:06:17Z","abstract_excerpt":"Large multilingual models have inspired a new class of word alignment methods, which work well for the model's pretraining languages. However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data. In this work, we ask: How do modern aligners perform on unseen languages, and are they better than traditional methods? We contribute gold-standard alignments for Bribri--Spanish, Guarani--Spanish, Quechua--Spanish, and Shipibo-Konibo--Spanish. With these, we evaluate state-of-the-art aligners with and without model adaptation to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07912","kind":"arxiv","version":1},"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/2302.07912/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.07912","created_at":"2026-07-05T05:42:31.804348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07912v1","created_at":"2026-07-05T05:42:31.804348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07912","created_at":"2026-07-05T05:42:31.804348+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYTTGTQNJZNK","created_at":"2026-07-05T05:42:31.804348+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYTTGTQNJZNK7N2J","created_at":"2026-07-05T05:42:31.804348+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYTTGTQN","created_at":"2026-07-05T05:42:31.804348+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK","json":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK.json","graph_json":"https://pith.science/api/pith-number/XYTTGTQNJZNK7N2J4UNUE6X5QK/graph.json","events_json":"https://pith.science/api/pith-number/XYTTGTQNJZNK7N2J4UNUE6X5QK/events.json","paper":"https://pith.science/paper/XYTTGTQN"},"agent_actions":{"view_html":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK","download_json":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK.json","view_paper":"https://pith.science/paper/XYTTGTQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07912&json=true","fetch_graph":"https://pith.science/api/pith-number/XYTTGTQNJZNK7N2J4UNUE6X5QK/graph.json","fetch_events":"https://pith.science/api/pith-number/XYTTGTQNJZNK7N2J4UNUE6X5QK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/action/storage_attestation","attest_author":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/action/author_attestation","sign_citation":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/action/citation_signature","submit_replication":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/action/replication_record"}},"created_at":"2026-07-05T05:42:31.804348+00:00","updated_at":"2026-07-05T05:42:31.804348+00:00"}