{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K4UXB3CXQD5KKKT26E6ETPYTFC","short_pith_number":"pith:K4UXB3CX","canonical_record":{"source":{"id":"2506.12966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T21:08:51Z","cross_cats_sorted":[],"title_canon_sha256":"34e8861fa7bcacf35cf2d8fd43db173b2d2f1ebe27d9dece0f546dcb5085de59","abstract_canon_sha256":"5f7acda20f9abfb68bcc137e5dd2fcd4dfe23764e5db694fd8407f921e42bbb3"},"schema_version":"1.0"},"canonical_sha256":"572970ec5780faa52a7af13c49bf1328aaaf0fbeba8dde87510c78aefa22efb0","source":{"kind":"arxiv","id":"2506.12966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12966","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12966v1","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12966","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"K4UXB3CXQD5K","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"K4UXB3CXQD5KKKT2","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"K4UXB3CX","created_at":"2026-07-05T11:22:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K4UXB3CXQD5KKKT26E6ETPYTFC","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T21:08:51Z","cross_cats_sorted":[],"title_canon_sha256":"34e8861fa7bcacf35cf2d8fd43db173b2d2f1ebe27d9dece0f546dcb5085de59","abstract_canon_sha256":"5f7acda20f9abfb68bcc137e5dd2fcd4dfe23764e5db694fd8407f921e42bbb3"},"schema_version":"1.0"},"canonical_sha256":"572970ec5780faa52a7af13c49bf1328aaaf0fbeba8dde87510c78aefa22efb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:03.094216Z","signature_b64":"TmW7CLHWFkorrhXxYG0mtzksAgHfGE6QO7wVDAyz7MNVqAXVvWFKD+QhyFxKil9Gyufdof7YtG3Lp/E9zcFeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572970ec5780faa52a7af13c49bf1328aaaf0fbeba8dde87510c78aefa22efb0","last_reissued_at":"2026-07-05T11:22:03.093825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:03.093825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12966","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":"2026-07-05T11:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkbjgQVLYuyDtntrBPuCy9M07N4wlHcoo79rkIVP5caPwqITY0lZvH5CEZPRo7wQqhyLB51XSa+FzVuYyz2JCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:47:19.266577Z"},"content_sha256":"c4308d2dffe06ac27b128eccab78bd83a84afa054e6e0544589af0fa7f8e3cbf","schema_version":"1.0","event_id":"sha256:c4308d2dffe06ac27b128eccab78bd83a84afa054e6e0544589af0fa7f8e3cbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K4UXB3CXQD5KKKT26E6ETPYTFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing the Role of Data Quality in Training Bilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Grangier, Maartje ter Hoeve, Maureen de Seyssel, Skyler Seto","submitted_at":"2025-06-15T21:08:51Z","abstract_excerpt":"Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages can degrade performance for some languages (such as English), while improving others (typically more data constrained languages). In this work, we investigate causes of these inconsistencies by comparing bilingual and monolingual language models. Our analysis reveals that unequal data quality, not just data quantity, is a major driver of performance degrada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12966","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/2506.12966/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":"2026-07-05T11:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KB6Kw3bOIQvrKBjxR+LoyMw07/0bWveFdCe4FEKgYif+seVPjVCKuIqRs3DAMSvFnpM1+Xxrj6TtAQS1IpmsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:47:19.267563Z"},"content_sha256":"9dde07cb0f827c4baf1d6bc383aefbf3f261a94e4cc86cce8ac26b00d2cadf39","schema_version":"1.0","event_id":"sha256:9dde07cb0f827c4baf1d6bc383aefbf3f261a94e4cc86cce8ac26b00d2cadf39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4UXB3CXQD5KKKT26E6ETPYTFC/bundle.json","state_url":"https://pith.science/pith/K4UXB3CXQD5KKKT26E6ETPYTFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4UXB3CXQD5KKKT26E6ETPYTFC/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":"2026-08-09T23:47:19Z","links":{"resolver":"https://pith.science/pith/K4UXB3CXQD5KKKT26E6ETPYTFC","bundle":"https://pith.science/pith/K4UXB3CXQD5KKKT26E6ETPYTFC/bundle.json","state":"https://pith.science/pith/K4UXB3CXQD5KKKT26E6ETPYTFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4UXB3CXQD5KKKT26E6ETPYTFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4UXB3CXQD5KKKT26E6ETPYTFC","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":"5f7acda20f9abfb68bcc137e5dd2fcd4dfe23764e5db694fd8407f921e42bbb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T21:08:51Z","title_canon_sha256":"34e8861fa7bcacf35cf2d8fd43db173b2d2f1ebe27d9dece0f546dcb5085de59"},"schema_version":"1.0","source":{"id":"2506.12966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12966","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12966v1","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12966","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"K4UXB3CXQD5K","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"K4UXB3CXQD5KKKT2","created_at":"2026-07-05T11:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"K4UXB3CX","created_at":"2026-07-05T11:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:9dde07cb0f827c4baf1d6bc383aefbf3f261a94e4cc86cce8ac26b00d2cadf39","target":"graph","created_at":"2026-07-05T11:22:03Z","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/2506.12966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages can degrade performance for some languages (such as English), while improving others (typically more data constrained languages). In this work, we investigate causes of these inconsistencies by comparing bilingual and monolingual language models. Our analysis reveals that unequal data quality, not just data quantity, is a major driver of performance degrada","authors_text":"David Grangier, Maartje ter Hoeve, Maureen de Seyssel, Skyler Seto","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T21:08:51Z","title":"Assessing the Role of Data Quality in Training Bilingual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12966","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:c4308d2dffe06ac27b128eccab78bd83a84afa054e6e0544589af0fa7f8e3cbf","target":"record","created_at":"2026-07-05T11:22:03Z","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":"5f7acda20f9abfb68bcc137e5dd2fcd4dfe23764e5db694fd8407f921e42bbb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T21:08:51Z","title_canon_sha256":"34e8861fa7bcacf35cf2d8fd43db173b2d2f1ebe27d9dece0f546dcb5085de59"},"schema_version":"1.0","source":{"id":"2506.12966","kind":"arxiv","version":1}},"canonical_sha256":"572970ec5780faa52a7af13c49bf1328aaaf0fbeba8dde87510c78aefa22efb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"572970ec5780faa52a7af13c49bf1328aaaf0fbeba8dde87510c78aefa22efb0","first_computed_at":"2026-07-05T11:22:03.093825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:03.093825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TmW7CLHWFkorrhXxYG0mtzksAgHfGE6QO7wVDAyz7MNVqAXVvWFKD+QhyFxKil9Gyufdof7YtG3Lp/E9zcFeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:03.094216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4308d2dffe06ac27b128eccab78bd83a84afa054e6e0544589af0fa7f8e3cbf","sha256:9dde07cb0f827c4baf1d6bc383aefbf3f261a94e4cc86cce8ac26b00d2cadf39"],"state_sha256":"c30052106eaf8279310b3cf8b1c0f161bd933cb5a8d6834acd8915105bddd90e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8PJ4+v3WfuYlrHwH+P7qSN8WPYWCp2FrSS3hfXxl/fy29FZUD9ATQ9SdSpsgJ8HtBqycK3WHZdPC1+kf0v1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:47:19.273092Z","bundle_sha256":"fc764cbee392ced48d6327d06b5dc3981e709648feda48b353f9971cfefe1c9e"}}