{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CMY5BI3JI5GKJRLF7W6ZYTZX7R","short_pith_number":"pith:CMY5BI3J","canonical_record":{"source":{"id":"2404.07982","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:58:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b9669eb3bbbcefb7ef41d24bdbb9aeeee85d15c43dfed2c94f32c94081e7e7e","abstract_canon_sha256":"49d85f0e0d50a527c61935663485f12238d8ad2e3e5ab690c07198120cf3ee06"},"schema_version":"1.0"},"canonical_sha256":"1331d0a369474ca4c565fdbd9c4f37fc56c1424eadec3184caf48044357d00e0","source":{"kind":"arxiv","id":"2404.07982","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07982","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07982v4","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07982","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"CMY5BI3JI5GK","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"CMY5BI3JI5GKJRLF","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"CMY5BI3J","created_at":"2026-07-05T08:44:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CMY5BI3JI5GKJRLF7W6ZYTZX7R","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07982","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:58:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b9669eb3bbbcefb7ef41d24bdbb9aeeee85d15c43dfed2c94f32c94081e7e7e","abstract_canon_sha256":"49d85f0e0d50a527c61935663485f12238d8ad2e3e5ab690c07198120cf3ee06"},"schema_version":"1.0"},"canonical_sha256":"1331d0a369474ca4c565fdbd9c4f37fc56c1424eadec3184caf48044357d00e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:53.661408Z","signature_b64":"7Zh1cBVxhJ8z3fjqPidBZfoXeYVY9j24k7NzdoYc6TuSjCOCHp9C8BogIoQYQ2E+mmPO4hMXicFTJ+XOdIWiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1331d0a369474ca4c565fdbd9c4f37fc56c1424eadec3184caf48044357d00e0","last_reissued_at":"2026-07-05T08:44:53.660909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:53.660909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07982","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2MZpC8z1EPz9TLlCTxL4IXxhmMKBXtyEcZgv3/1Uk4cVRYiKsFsAUJrI+GWGKc1Y2vJjdJKDTGynC+ykrdvbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:25:07.215662Z"},"content_sha256":"a6f9b6add55167f286bbcb5357f3fc8bcfafb2486afcbd0a8ba2298452eaf199","schema_version":"1.0","event_id":"sha256:a6f9b6add55167f286bbcb5357f3fc8bcfafb2486afcbd0a8ba2298452eaf199"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CMY5BI3JI5GKJRLF7W6ZYTZX7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anton Sch\\\"afer, Imanol Schlag, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel","submitted_at":"2024-04-11T17:58:05Z","abstract_excerpt":"Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations, allowing what is learned in one language to generalise to others. Prior research has emphasised the importance of parallel data and shared vocabulary elements as key factors for such alignment. In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. In controlled experiments on perfectly equivalent cloned l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07982","kind":"arxiv","version":4},"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/2404.07982/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":"2026-07-05T08:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LlDJDmjbSbBA+d3Ad6TzYwAvsCObJK9vMEXsoAXtkDlvmNdJhrgBHh65/z9NvDJbx0XlM/UokufQdwUay1DqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:25:07.216047Z"},"content_sha256":"991a16616826f6df184e4d581da6f12e05a693443ebd4ab49b4da347971a4162","schema_version":"1.0","event_id":"sha256:991a16616826f6df184e4d581da6f12e05a693443ebd4ab49b4da347971a4162"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R/bundle.json","state_url":"https://pith.science/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R/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":"2026-08-05T03:25:07Z","links":{"resolver":"https://pith.science/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R","bundle":"https://pith.science/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R/bundle.json","state":"https://pith.science/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMY5BI3JI5GKJRLF7W6ZYTZX7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CMY5BI3JI5GKJRLF7W6ZYTZX7R","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":"49d85f0e0d50a527c61935663485f12238d8ad2e3e5ab690c07198120cf3ee06","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:58:05Z","title_canon_sha256":"1b9669eb3bbbcefb7ef41d24bdbb9aeeee85d15c43dfed2c94f32c94081e7e7e"},"schema_version":"1.0","source":{"id":"2404.07982","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07982","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07982v4","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07982","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"CMY5BI3JI5GK","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"CMY5BI3JI5GKJRLF","created_at":"2026-07-05T08:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"CMY5BI3J","created_at":"2026-07-05T08:44:53Z"}],"graph_snapshots":[{"event_id":"sha256:991a16616826f6df184e4d581da6f12e05a693443ebd4ab49b4da347971a4162","target":"graph","created_at":"2026-07-05T08:44:53Z","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/2404.07982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations, allowing what is learned in one language to generalise to others. Prior research has emphasised the importance of parallel data and shared vocabulary elements as key factors for such alignment. In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. In controlled experiments on perfectly equivalent cloned l","authors_text":"Anton Sch\\\"afer, Imanol Schlag, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:58:05Z","title":"The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07982","kind":"arxiv","version":4},"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:a6f9b6add55167f286bbcb5357f3fc8bcfafb2486afcbd0a8ba2298452eaf199","target":"record","created_at":"2026-07-05T08:44:53Z","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":"49d85f0e0d50a527c61935663485f12238d8ad2e3e5ab690c07198120cf3ee06","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:58:05Z","title_canon_sha256":"1b9669eb3bbbcefb7ef41d24bdbb9aeeee85d15c43dfed2c94f32c94081e7e7e"},"schema_version":"1.0","source":{"id":"2404.07982","kind":"arxiv","version":4}},"canonical_sha256":"1331d0a369474ca4c565fdbd9c4f37fc56c1424eadec3184caf48044357d00e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1331d0a369474ca4c565fdbd9c4f37fc56c1424eadec3184caf48044357d00e0","first_computed_at":"2026-07-05T08:44:53.660909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:53.660909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Zh1cBVxhJ8z3fjqPidBZfoXeYVY9j24k7NzdoYc6TuSjCOCHp9C8BogIoQYQ2E+mmPO4hMXicFTJ+XOdIWiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:53.661408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07982","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6f9b6add55167f286bbcb5357f3fc8bcfafb2486afcbd0a8ba2298452eaf199","sha256:991a16616826f6df184e4d581da6f12e05a693443ebd4ab49b4da347971a4162"],"state_sha256":"795d01ede1ebe83640334808297ea8f0eafe1321c98e3e120fc7ac9e3aaeadb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MbN822khgEjZ3wCvitiVQLEfQnHi9mwiRDCIqWgvG3McnRg5C9Xfnx++HsmeweyCU2PsoQwkzosd1ZVMGpaUDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:25:07.218403Z","bundle_sha256":"b05bd3bcc2dad4b3d3cf992d705817e1e2c25f1bff3a81e691716120defbf5c3"}}