{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LLDGLWWGYFMX5SNUGBB47AVTQW","short_pith_number":"pith:LLDGLWWG","schema_version":"1.0","canonical_sha256":"5ac665dac6c1597ec9b43043cf82b385bd95346892a26644beeacc0b309898f3","source":{"kind":"arxiv","id":"2402.03131","version":1},"attestation_state":"computed","paper":{"title":"Constrained Decoding for Cross-lingual Label Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Duong Minh Le, Wei Xu, Yang Chen","submitted_at":"2024-02-05T15:57:32Z","abstract_excerpt":"Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases, the performance of zero-shot cross-lingual transfer learning lags far behind supervised fine-tuning methods. Therefore, it is common to exploit translation and label projection to further improve the performance by (1) translating training data that is available in a high-resource language (e.g., English) together with the gold labels into low-resource lang"},"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":"2402.03131","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T15:57:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5100f4d321676454f0572a21ebd622a9b7271c4760bb70629561294c6bbdcd19","abstract_canon_sha256":"f7df88ea1e4b91a9118dbcd7c7c1e41f1d0d2f6d0c3f813bc66d5a9232ff6e69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:31.592714Z","signature_b64":"qeKqUbjeR0Je1ol95/awgpw7KdehRpCp1i5bHV9NjFYT7ph5sFKqTrvA5Lwf0hnIVhTlVg9HX1g0gaamiLdjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ac665dac6c1597ec9b43043cf82b385bd95346892a26644beeacc0b309898f3","last_reissued_at":"2026-07-05T07:41:31.592220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:31.592220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Decoding for Cross-lingual Label Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Duong Minh Le, Wei Xu, Yang Chen","submitted_at":"2024-02-05T15:57:32Z","abstract_excerpt":"Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases, the performance of zero-shot cross-lingual transfer learning lags far behind supervised fine-tuning methods. Therefore, it is common to exploit translation and label projection to further improve the performance by (1) translating training data that is available in a high-resource language (e.g., English) together with the gold labels into low-resource lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03131","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/2402.03131/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":"2402.03131","created_at":"2026-07-05T07:41:31.592277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03131v1","created_at":"2026-07-05T07:41:31.592277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03131","created_at":"2026-07-05T07:41:31.592277+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLDGLWWGYFMX","created_at":"2026-07-05T07:41:31.592277+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLDGLWWGYFMX5SNU","created_at":"2026-07-05T07:41:31.592277+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLDGLWWG","created_at":"2026-07-05T07:41:31.592277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18750","citing_title":"Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW","json":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW.json","graph_json":"https://pith.science/api/pith-number/LLDGLWWGYFMX5SNUGBB47AVTQW/graph.json","events_json":"https://pith.science/api/pith-number/LLDGLWWGYFMX5SNUGBB47AVTQW/events.json","paper":"https://pith.science/paper/LLDGLWWG"},"agent_actions":{"view_html":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW","download_json":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW.json","view_paper":"https://pith.science/paper/LLDGLWWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03131&json=true","fetch_graph":"https://pith.science/api/pith-number/LLDGLWWGYFMX5SNUGBB47AVTQW/graph.json","fetch_events":"https://pith.science/api/pith-number/LLDGLWWGYFMX5SNUGBB47AVTQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW/action/storage_attestation","attest_author":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW/action/author_attestation","sign_citation":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW/action/citation_signature","submit_replication":"https://pith.science/pith/LLDGLWWGYFMX5SNUGBB47AVTQW/action/replication_record"}},"created_at":"2026-07-05T07:41:31.592277+00:00","updated_at":"2026-07-05T07:41:31.592277+00:00"}