{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5HASAWWR573WBBLVFPYP6GTV6C","short_pith_number":"pith:5HASAWWR","canonical_record":{"source":{"id":"2402.13016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T13:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"9fe528bd273b86367b479e50eeed6e454cc9630867bdccc1093474b8de049e59","abstract_canon_sha256":"278cef3b604a72c1cd1ab2b345921d90211f770f5089514964d3965d57bde41a"},"schema_version":"1.0"},"canonical_sha256":"e9c1205ad1eff76085752bf0ff1a75f0b4d5942be9bf891b823a7641c62d45de","source":{"kind":"arxiv","id":"2402.13016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13016","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13016v1","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13016","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"pith_short_12","alias_value":"5HASAWWR573W","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"pith_short_16","alias_value":"5HASAWWR573WBBLV","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"pith_short_8","alias_value":"5HASAWWR","created_at":"2026-07-05T07:47:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5HASAWWR573WBBLVFPYP6GTV6C","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T13:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"9fe528bd273b86367b479e50eeed6e454cc9630867bdccc1093474b8de049e59","abstract_canon_sha256":"278cef3b604a72c1cd1ab2b345921d90211f770f5089514964d3965d57bde41a"},"schema_version":"1.0"},"canonical_sha256":"e9c1205ad1eff76085752bf0ff1a75f0b4d5942be9bf891b823a7641c62d45de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:19.692433Z","signature_b64":"h5ys3iMPGBwpXx+D9VlYLQYX83Y+30HlQHbAlsV8+2bxaLGI/p2oXv+8HoxtLKree+wpCyo9Z9a59OFuPHajDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9c1205ad1eff76085752bf0ff1a75f0b4d5942be9bf891b823a7641c62d45de","last_reissued_at":"2026-07-05T07:47:19.691961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:19.691961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13016","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":"2026-07-05T07:47:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jP1UC2AVaiAlfoMcmnIuFVejp45BWzak16Dth86bCc65/fcLjk5EGWaMe7ruRHdSasXRm2sB+YWRA0Vh55erAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:59:30.008911Z"},"content_sha256":"655f48e4a76e4e0052e15e1060a7f567fac8e4298c74839cf2490b9fa37ce673","schema_version":"1.0","event_id":"sha256:655f48e4a76e4e0052e15e1060a7f567fac8e4298c74839cf2490b9fa37ce673"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5HASAWWR573WBBLVFPYP6GTV6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the effects of language-specific class imbalance in multilingual fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lonneke van der Plas, Vincent Jung","submitted_at":"2024-02-20T13:59:12Z","abstract_excerpt":"We study the effect of one type of imbalance often present in real-life multilingual classification datasets: an uneven distribution of labels across languages. We show evidence that fine-tuning a transformer-based Large Language Model (LLM) on a dataset with this imbalance leads to worse performance, a more pronounced separation of languages in the latent space, and the promotion of uninformative features. We modify the traditional class weighing approach to imbalance by calculating class weights separately for each language and show that this helps mitigate those detrimental effects. These r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13016","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/2402.13016/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":"2026-07-05T07:47:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1JHW+Vsx4JllbqgSbXUEAjYS7YheKgAxXiAsQ1V2L7R0RWNdC1i785T9jqpJfiebSj+85d+bAM/v8O0qmB8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:59:30.009390Z"},"content_sha256":"49ebf48f5e314bf6acc2682961c4df95b22447912529bd700521ef96674eec15","schema_version":"1.0","event_id":"sha256:49ebf48f5e314bf6acc2682961c4df95b22447912529bd700521ef96674eec15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HASAWWR573WBBLVFPYP6GTV6C/bundle.json","state_url":"https://pith.science/pith/5HASAWWR573WBBLVFPYP6GTV6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HASAWWR573WBBLVFPYP6GTV6C/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":"2026-08-09T11:59:30Z","links":{"resolver":"https://pith.science/pith/5HASAWWR573WBBLVFPYP6GTV6C","bundle":"https://pith.science/pith/5HASAWWR573WBBLVFPYP6GTV6C/bundle.json","state":"https://pith.science/pith/5HASAWWR573WBBLVFPYP6GTV6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HASAWWR573WBBLVFPYP6GTV6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5HASAWWR573WBBLVFPYP6GTV6C","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":"278cef3b604a72c1cd1ab2b345921d90211f770f5089514964d3965d57bde41a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T13:59:12Z","title_canon_sha256":"9fe528bd273b86367b479e50eeed6e454cc9630867bdccc1093474b8de049e59"},"schema_version":"1.0","source":{"id":"2402.13016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13016","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13016v1","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13016","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"pith_short_12","alias_value":"5HASAWWR573W","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"pith_short_16","alias_value":"5HASAWWR573WBBLV","created_at":"2026-07-05T07:47:19Z"},{"alias_kind":"pith_short_8","alias_value":"5HASAWWR","created_at":"2026-07-05T07:47:19Z"}],"graph_snapshots":[{"event_id":"sha256:49ebf48f5e314bf6acc2682961c4df95b22447912529bd700521ef96674eec15","target":"graph","created_at":"2026-07-05T07:47:19Z","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/2402.13016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the effect of one type of imbalance often present in real-life multilingual classification datasets: an uneven distribution of labels across languages. We show evidence that fine-tuning a transformer-based Large Language Model (LLM) on a dataset with this imbalance leads to worse performance, a more pronounced separation of languages in the latent space, and the promotion of uninformative features. We modify the traditional class weighing approach to imbalance by calculating class weights separately for each language and show that this helps mitigate those detrimental effects. These r","authors_text":"Lonneke van der Plas, Vincent Jung","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T13:59:12Z","title":"Understanding the effects of language-specific class imbalance in multilingual fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13016","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":"sha256:655f48e4a76e4e0052e15e1060a7f567fac8e4298c74839cf2490b9fa37ce673","target":"record","created_at":"2026-07-05T07:47:19Z","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":"278cef3b604a72c1cd1ab2b345921d90211f770f5089514964d3965d57bde41a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T13:59:12Z","title_canon_sha256":"9fe528bd273b86367b479e50eeed6e454cc9630867bdccc1093474b8de049e59"},"schema_version":"1.0","source":{"id":"2402.13016","kind":"arxiv","version":1}},"canonical_sha256":"e9c1205ad1eff76085752bf0ff1a75f0b4d5942be9bf891b823a7641c62d45de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9c1205ad1eff76085752bf0ff1a75f0b4d5942be9bf891b823a7641c62d45de","first_computed_at":"2026-07-05T07:47:19.691961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:19.691961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5ys3iMPGBwpXx+D9VlYLQYX83Y+30HlQHbAlsV8+2bxaLGI/p2oXv+8HoxtLKree+wpCyo9Z9a59OFuPHajDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:19.692433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:655f48e4a76e4e0052e15e1060a7f567fac8e4298c74839cf2490b9fa37ce673","sha256:49ebf48f5e314bf6acc2682961c4df95b22447912529bd700521ef96674eec15"],"state_sha256":"849a1dde16f3424c8ddccf72fa68f05758592f77a6eba09802d85bafcdbbdaa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MPuJ0TAE6RQjC4xxinc/UeSCalUbzN9L90iZVrt3ui/tPAXX0m60qxn9ao16QUpxhiqsr8a8LfDsjl0wTbjfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:59:30.013003Z","bundle_sha256":"cc1eec0f80dc3d0186d3b725bb36c5a2bc44062b051ed917683455071eefe8ae"}}