{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G523BRXOR4R2YAPAK5SZBIML2V","short_pith_number":"pith:G523BRXO","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"},"canonical_sha256":"3775b0c6ee8f23ac01e0576590a18bd5466035633b347bafd0c524f9c4219e67","source":{"kind":"arxiv","id":"2311.06379","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06379","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06379v1","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06379","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"G523BRXOR4R2","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"G523BRXOR4R2YAPA","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"G523BRXO","created_at":"2026-07-05T07:11:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G523BRXOR4R2YAPAK5SZBIML2V","target":"record","payload":{"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"},"canonical_sha256":"3775b0c6ee8f23ac01e0576590a18bd5466035633b347bafd0c524f9c4219e67","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"},"source_kind":"arxiv","source_id":"2311.06379","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ld58Tqq2uwDjgrvULf7Nly1wQpybrlSyd3SP4VLEt0k/+189PpQk1lyCc7c6wbCojhHev0Ve8Abh1BlV3hRtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:51:57.753682Z"},"content_sha256":"12034c793eb8bdb506c9e9d07d64aea29e3e03b8fa071dd7c12c46a088b37bba","schema_version":"1.0","event_id":"sha256:12034c793eb8bdb506c9e9d07d64aea29e3e03b8fa071dd7c12c46a088b37bba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G523BRXOR4R2YAPAK5SZBIML2V","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijTKW3U+/plo/t7s3SuG8zuVaOPMGevWxBIuW7AAc2xnwLXycsghMVfo19za2asg5NjmAqPwkR3qXeoFuptLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:51:57.754172Z"},"content_sha256":"c6775ed1392511ce6580b13b743f5e1f4d9c9ccbdaa58d39cd7b06527cbe9cf6","schema_version":"1.0","event_id":"sha256:c6775ed1392511ce6580b13b743f5e1f4d9c9ccbdaa58d39cd7b06527cbe9cf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/bundle.json","state_url":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G523BRXOR4R2YAPAK5SZBIML2V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T07:51:57Z","links":{"resolver":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V","bundle":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/bundle.json","state":"https://pith.science/pith/G523BRXOR4R2YAPAK5SZBIML2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G523BRXOR4R2YAPAK5SZBIML2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G523BRXOR4R2YAPAK5SZBIML2V","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":"c1e3c62127235b49f92f869d2ed245e0ae6dee88cd1dc63a535360d609251ad9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T20:09:08Z","title_canon_sha256":"8894cdfcef2cc449c58fb71152a58fffc66e1efc4b7c4ba42a08604d52644626"},"schema_version":"1.0","source":{"id":"2311.06379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06379","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06379v1","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06379","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"G523BRXOR4R2","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"G523BRXOR4R2YAPA","created_at":"2026-07-05T07:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"G523BRXO","created_at":"2026-07-05T07:11:39Z"}],"graph_snapshots":[{"event_id":"sha256:c6775ed1392511ce6580b13b743f5e1f4d9c9ccbdaa58d39cd7b06527cbe9cf6","target":"graph","created_at":"2026-07-05T07:11:39Z","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/2311.06379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Graham Neubig, Lucio Dery, Simran Khanuja, Srinivas Gowriraj","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T20:09:08Z","title":"DeMuX: Data-efficient Multilingual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06379","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":"sha256:12034c793eb8bdb506c9e9d07d64aea29e3e03b8fa071dd7c12c46a088b37bba","target":"record","created_at":"2026-07-05T07:11:39Z","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":"c1e3c62127235b49f92f869d2ed245e0ae6dee88cd1dc63a535360d609251ad9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T20:09:08Z","title_canon_sha256":"8894cdfcef2cc449c58fb71152a58fffc66e1efc4b7c4ba42a08604d52644626"},"schema_version":"1.0","source":{"id":"2311.06379","kind":"arxiv","version":1}},"canonical_sha256":"3775b0c6ee8f23ac01e0576590a18bd5466035633b347bafd0c524f9c4219e67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3775b0c6ee8f23ac01e0576590a18bd5466035633b347bafd0c524f9c4219e67","first_computed_at":"2026-07-05T07:11:39.184915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:39.184915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FSGFI2X2CnL2OXR+B+s6NuVBiKRHs3aivEY1YwXTNtE5HckFg1ugFgI8+ORXbzqncZ/PuzN1anb6rz3PpX6EDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:39.185367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12034c793eb8bdb506c9e9d07d64aea29e3e03b8fa071dd7c12c46a088b37bba","sha256:c6775ed1392511ce6580b13b743f5e1f4d9c9ccbdaa58d39cd7b06527cbe9cf6"],"state_sha256":"f61994f8d230c91dc4103a1c7354c21ba78a0af8fd8a09fb77239f4ffe3abf3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Oh40p5m1NBtwqiyL8YqPxgRBDVyk5HLXeu9T/5Y0Ie0p1ht195d2Q3298HRLX36yuALUvJLT27F56vqrta1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:51:57.757773Z","bundle_sha256":"1e2a8063baad94b8f0d5980a1d9e38c84252c8e7e1ada207d9043081b9f98ee4"}}