{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I6OOHVRDHIZQ2RGESEZ3NH2JLC","short_pith_number":"pith:I6OOHVRD","schema_version":"1.0","canonical_sha256":"479ce3d6233a330d44c49133b69f49588296403d3e867df547f9764258f5dc56","source":{"kind":"arxiv","id":"2106.03830","version":2},"attestation_state":"computed","paper":{"title":"A Simple Recipe for Multilingual Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aliaksei Severyn, Eric Malmi, Jonathan Mallinson, Sascha Rothe, Sebastian Krause","submitted_at":"2021-06-07T17:47:04Z","abstract_excerpt":"This paper presents a simple recipe to train state-of-the-art multilingual Grammatical Error Correction (GEC) models. We achieve this by first proposing a language-agnostic method to generate a large number of synthetic examples. The second ingredient is to use large-scale multilingual language models (up to 11B parameters). Once fine-tuned on language-specific supervised sets we surpass the previous state-of-the-art results on GEC benchmarks in four languages: English, Czech, German and Russian. Having established a new set of baselines for GEC, we make our results easily reproducible and acc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.03830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T17:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"3ee34b093a86c35232073b43ce683f6db11a09bb61aba799712ed7efdcce0331","abstract_canon_sha256":"1e6b903f3254662030d312593694ac1bad82d05e8d271cb3c144b2bc46cb1470"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:51.384393Z","signature_b64":"xe9rQzRxAIp1J91PUOwm3H0zyRUTMJHdi4vpiMKxkA35lfxxWDVKxHREM/wCgaYT6SN3RCbT0fKTrqfu+891Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"479ce3d6233a330d44c49133b69f49588296403d3e867df547f9764258f5dc56","last_reissued_at":"2026-07-05T04:46:51.383844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:51.383844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Recipe for Multilingual Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aliaksei Severyn, Eric Malmi, Jonathan Mallinson, Sascha Rothe, Sebastian Krause","submitted_at":"2021-06-07T17:47:04Z","abstract_excerpt":"This paper presents a simple recipe to train state-of-the-art multilingual Grammatical Error Correction (GEC) models. We achieve this by first proposing a language-agnostic method to generate a large number of synthetic examples. The second ingredient is to use large-scale multilingual language models (up to 11B parameters). Once fine-tuned on language-specific supervised sets we surpass the previous state-of-the-art results on GEC benchmarks in four languages: English, Czech, German and Russian. Having established a new set of baselines for GEC, we make our results easily reproducible and acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03830","kind":"arxiv","version":2},"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/2106.03830/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.03830","created_at":"2026-07-05T04:46:51.383901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03830v2","created_at":"2026-07-05T04:46:51.383901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03830","created_at":"2026-07-05T04:46:51.383901+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6OOHVRDHIZQ","created_at":"2026-07-05T04:46:51.383901+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6OOHVRDHIZQ2RGE","created_at":"2026-07-05T04:46:51.383901+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6OOHVRD","created_at":"2026-07-05T04:46:51.383901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2202.08906","citing_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","ref_index":191,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC","json":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC.json","graph_json":"https://pith.science/api/pith-number/I6OOHVRDHIZQ2RGESEZ3NH2JLC/graph.json","events_json":"https://pith.science/api/pith-number/I6OOHVRDHIZQ2RGESEZ3NH2JLC/events.json","paper":"https://pith.science/paper/I6OOHVRD"},"agent_actions":{"view_html":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC","download_json":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC.json","view_paper":"https://pith.science/paper/I6OOHVRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03830&json=true","fetch_graph":"https://pith.science/api/pith-number/I6OOHVRDHIZQ2RGESEZ3NH2JLC/graph.json","fetch_events":"https://pith.science/api/pith-number/I6OOHVRDHIZQ2RGESEZ3NH2JLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC/action/storage_attestation","attest_author":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC/action/author_attestation","sign_citation":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC/action/citation_signature","submit_replication":"https://pith.science/pith/I6OOHVRDHIZQ2RGESEZ3NH2JLC/action/replication_record"}},"created_at":"2026-07-05T04:46:51.383901+00:00","updated_at":"2026-07-05T04:46:51.383901+00:00"}