{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NMTF73XTCMFJAWPCBTOVJJHIHZ","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":"038912992f7da1c9050128aa05727d49964e5793e193518209f26e8d9e967914","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-03T23:12:27Z","title_canon_sha256":"0fb41a3b9d0e62f70f00929042c975e3355e5b2bbd20494ae05ace5b0e7951a8"},"schema_version":"1.0","source":{"id":"2106.02171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02171","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02171v1","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02171","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"NMTF73XTCMFJ","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"NMTF73XTCMFJAWPC","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"NMTF73XT","created_at":"2026-07-05T02:46:16Z"}],"graph_snapshots":[{"event_id":"sha256:1677a6a0062e441954f0440974cf3d1fcdfc5e31dc98fc62f9b21f6d4458ae49","target":"graph","created_at":"2026-07-05T02:46:16Z","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/2106.02171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In this paper, we investigate the impact of incorporating parallel data into mT5 pre-training. We find that multi-tasking language modeling with objectives such as machine translation during pre-training is a straightforward way to improve performance on downstream multilingual and cross-lingual tasks. However, the gains start to diminish as the model capacity increases, suggesting that parallel data might not be as ess","authors_text":"Aditya Siddhant, Linting Xue, Melvin Johnson, Mihir Kale, Noah Constant, Rami Al-Rfou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-03T23:12:27Z","title":"nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02171","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":"sha256:7409e9b3c573d950211ec36252cf73dad8e28f515bcb6645c4aa44f48d1578e5","target":"record","created_at":"2026-07-05T02:46:16Z","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":"038912992f7da1c9050128aa05727d49964e5793e193518209f26e8d9e967914","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-03T23:12:27Z","title_canon_sha256":"0fb41a3b9d0e62f70f00929042c975e3355e5b2bbd20494ae05ace5b0e7951a8"},"schema_version":"1.0","source":{"id":"2106.02171","kind":"arxiv","version":1}},"canonical_sha256":"6b265feef3130a9059e20cdd54a4e83e696d7a30fe4d6ee9e0a3badbf246e0ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b265feef3130a9059e20cdd54a4e83e696d7a30fe4d6ee9e0a3badbf246e0ba","first_computed_at":"2026-07-05T02:46:16.137814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:16.137814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SyCBEe8lWzqFfwyZWBV9zu4GYzQ2XlvvpQ1RLgLxS8FyVw4RZsdSqW/LJYCVw1fCQtNFGnucbXPqlO+ohpuyCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:16.138222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7409e9b3c573d950211ec36252cf73dad8e28f515bcb6645c4aa44f48d1578e5","sha256:1677a6a0062e441954f0440974cf3d1fcdfc5e31dc98fc62f9b21f6d4458ae49"],"state_sha256":"6575aa8514f42533a06cfeaa2035f3312b98ac63c0a09f2aca6664c558f51af5"}