{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G523BRXOR4R2YAPAK5SZBIML2V","short_pith_number":"pith:G523BRXO","schema_version":"1.0","canonical_sha256":"3775b0c6ee8f23ac01e0576590a18bd5466035633b347bafd0c524f9c4219e67","source":{"kind":"arxiv","id":"2311.06379","version":1},"attestation_state":"computed","paper":{"title":"DeMuX: Data-efficient Multilingual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Lucio Dery, Simran Khanuja, Srinivas Gowriraj","submitted_at":"2023-11-10T20:09:08Z","abstract_excerpt":"We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to label from vast amounts of unlabelled multilingual data, having unknown degrees of overlap with the target set. Unlike most prior works, our end-to-end framework is language-agnostic, accounts for model representations, and supports multilingual target configurations. Our active learning strategies rely upon distance and uncertainty measures to select task-sp"},"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":"2311.06379","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T20:09:08Z","cross_cats_sorted":[],"title_canon_sha256":"8894cdfcef2cc449c58fb71152a58fffc66e1efc4b7c4ba42a08604d52644626","abstract_canon_sha256":"c1e3c62127235b49f92f869d2ed245e0ae6dee88cd1dc63a535360d609251ad9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:39.185367Z","signature_b64":"FSGFI2X2CnL2OXR+B+s6NuVBiKRHs3aivEY1YwXTNtE5HckFg1ugFgI8+ORXbzqncZ/PuzN1anb6rz3PpX6EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3775b0c6ee8f23ac01e0576590a18bd5466035633b347bafd0c524f9c4219e67","last_reissued_at":"2026-07-05T07:11:39.184915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:39.184915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeMuX: Data-efficient Multilingual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Lucio Dery, Simran Khanuja, Srinivas Gowriraj","submitted_at":"2023-11-10T20:09:08Z","abstract_excerpt":"We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to label from vast amounts of unlabelled multilingual data, having unknown degrees of overlap with the target set. Unlike most prior works, our end-to-end framework is language-agnostic, accounts for model representations, and supports multilingual target configurations. Our active learning strategies rely upon distance and uncertainty measures to select task-sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06379","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/2311.06379/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":"2311.06379","created_at":"2026-07-05T07:11:39.184971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06379v1","created_at":"2026-07-05T07:11:39.184971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06379","created_at":"2026-07-05T07:11:39.184971+00:00"},{"alias_kind":"pith_short_12","alias_value":"G523BRXOR4R2","created_at":"2026-07-05T07:11:39.184971+00:00"},{"alias_kind":"pith_short_16","alias_value":"G523BRXOR4R2YAPA","created_at":"2026-07-05T07:11:39.184971+00:00"},{"alias_kind":"pith_short_8","alias_value":"G523BRXO","created_at":"2026-07-05T07:11:39.184971+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/G523BRXOR4R2YAPAK5SZBIML2V","json":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V.json","graph_json":"https://pith.science/api/pith-number/G523BRXOR4R2YAPAK5SZBIML2V/graph.json","events_json":"https://pith.science/api/pith-number/G523BRXOR4R2YAPAK5SZBIML2V/events.json","paper":"https://pith.science/paper/G523BRXO"},"agent_actions":{"view_html":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V","download_json":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V.json","view_paper":"https://pith.science/paper/G523BRXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06379&json=true","fetch_graph":"https://pith.science/api/pith-number/G523BRXOR4R2YAPAK5SZBIML2V/graph.json","fetch_events":"https://pith.science/api/pith-number/G523BRXOR4R2YAPAK5SZBIML2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/action/storage_attestation","attest_author":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/action/author_attestation","sign_citation":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/action/citation_signature","submit_replication":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/action/replication_record"}},"created_at":"2026-07-05T07:11:39.184971+00:00","updated_at":"2026-07-05T07:11:39.184971+00:00"}