{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EZANXIOS4NZIA7D3EGMAD2LW3","short_pith_number":"pith:6EZANXIO","schema_version":"1.0","canonical_sha256":"f13206dd0e971b9403e3d90cc00f4bb6caa5b77a0dc45a5d24f6f7c9c372add4","source":{"kind":"arxiv","id":"2403.20157","version":1},"attestation_state":"computed","paper":{"title":"A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francois Meyer, Jan Buys","submitted_at":"2024-03-29T13:09:23Z","abstract_excerpt":"Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations. This paper studies the role of subword segmentation in cross-lingual transfer. We systematically compare the efficacy of several subword methods in promoting synergy and preventing interference across different linguistic typologies. Our findings show that subword regularisation boosts synergy in multilingual modelling, whereas BPE more effectively facilitates transfer during cross-lingual fine-tuning. Notably, our results suggest that differences in orthographic wo"},"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":"2403.20157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T13:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"ef1466fd69caf53b15a794fa22d2308fe977610ffb19b1e0ee2ae4345967d2c8","abstract_canon_sha256":"a0aa72d9da02679720dd11414a75e6efa46ceeca7ff12749a7a7792743652490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:14.556210Z","signature_b64":"G7x6YH8E5FNsTZN+HP6cTQjOlPxaUhUA5zZezYTcd/dHCf3hx2b+FRl/+KD5KTcv+OH8ReHcwMptVxcb/LeTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f13206dd0e971b9403e3d90cc00f4bb6caa5b77a0dc45a5d24f6f7c9c372add4","last_reissued_at":"2026-07-05T08:02:14.555751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:14.555751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francois Meyer, Jan Buys","submitted_at":"2024-03-29T13:09:23Z","abstract_excerpt":"Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations. This paper studies the role of subword segmentation in cross-lingual transfer. We systematically compare the efficacy of several subword methods in promoting synergy and preventing interference across different linguistic typologies. Our findings show that subword regularisation boosts synergy in multilingual modelling, whereas BPE more effectively facilitates transfer during cross-lingual fine-tuning. Notably, our results suggest that differences in orthographic wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20157","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/2403.20157/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":"2403.20157","created_at":"2026-07-05T08:02:14.555834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20157v1","created_at":"2026-07-05T08:02:14.555834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20157","created_at":"2026-07-05T08:02:14.555834+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EZANXIOS4NZ","created_at":"2026-07-05T08:02:14.555834+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EZANXIOS4NZIA7D","created_at":"2026-07-05T08:02:14.555834+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EZANXIO","created_at":"2026-07-05T08:02:14.555834+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/6EZANXIOS4NZIA7D3EGMAD2LW3","json":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3.json","graph_json":"https://pith.science/api/pith-number/6EZANXIOS4NZIA7D3EGMAD2LW3/graph.json","events_json":"https://pith.science/api/pith-number/6EZANXIOS4NZIA7D3EGMAD2LW3/events.json","paper":"https://pith.science/paper/6EZANXIO"},"agent_actions":{"view_html":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3","download_json":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3.json","view_paper":"https://pith.science/paper/6EZANXIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20157&json=true","fetch_graph":"https://pith.science/api/pith-number/6EZANXIOS4NZIA7D3EGMAD2LW3/graph.json","fetch_events":"https://pith.science/api/pith-number/6EZANXIOS4NZIA7D3EGMAD2LW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3/action/storage_attestation","attest_author":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3/action/author_attestation","sign_citation":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3/action/citation_signature","submit_replication":"https://pith.science/pith/6EZANXIOS4NZIA7D3EGMAD2LW3/action/replication_record"}},"created_at":"2026-07-05T08:02:14.555834+00:00","updated_at":"2026-07-05T08:02:14.555834+00:00"}