{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G3M6Y2IESZ23S36SRANHRNJKK3","short_pith_number":"pith:G3M6Y2IE","schema_version":"1.0","canonical_sha256":"36d9ec69049675b96fd2881a78b52a56e6f15fb4e37ad53ef6bd5cd89c45fc26","source":{"kind":"arxiv","id":"2008.02976","version":2},"attestation_state":"computed","paper":{"title":"Data Weighted Training Strategies for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Chris Alberti, Jared Lichtarge, Shankar Kumar","submitted_at":"2020-08-07T03:30:14Z","abstract_excerpt":"Recent progress in the task of Grammatical Error Correction (GEC) has been driven by addressing data sparsity, both through new methods for generating large and noisy pretraining data and through the publication of small and higher-quality finetuning data in the BEA-2019 shared task. Building upon recent work in Neural Machine Translation (NMT), we make use of both kinds of data by deriving example-level scores on our large pretraining data based on a smaller, higher-quality dataset. In this work, we perform an empirical study to discover how to best incorporate delta-log-perplexity, a type of"},"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":"2008.02976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-07T03:30:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbbb22c97d52aee3f6ef6090fed5a5473d3011d26102cf02aeb97dea4b05b377","abstract_canon_sha256":"cd3a553bc81d746cb2f4b4cf78b10ef33d9c0223039d3e2858126ee4e68af3c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:11.446406Z","signature_b64":"ORxjFe2TvUXqawPz7fx3g5bhpuaZT6579IET3MVq6sQ3KMsm/OoXy3UB5BCMg2UK6PIizxBy0XApL8F/nBCNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d9ec69049675b96fd2881a78b52a56e6f15fb4e37ad53ef6bd5cd89c45fc26","last_reissued_at":"2026-07-05T01:34:11.445985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:11.445985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Weighted Training Strategies for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Chris Alberti, Jared Lichtarge, Shankar Kumar","submitted_at":"2020-08-07T03:30:14Z","abstract_excerpt":"Recent progress in the task of Grammatical Error Correction (GEC) has been driven by addressing data sparsity, both through new methods for generating large and noisy pretraining data and through the publication of small and higher-quality finetuning data in the BEA-2019 shared task. Building upon recent work in Neural Machine Translation (NMT), we make use of both kinds of data by deriving example-level scores on our large pretraining data based on a smaller, higher-quality dataset. In this work, we perform an empirical study to discover how to best incorporate delta-log-perplexity, a type of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02976","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/2008.02976/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":"2008.02976","created_at":"2026-07-05T01:34:11.446041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02976v2","created_at":"2026-07-05T01:34:11.446041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02976","created_at":"2026-07-05T01:34:11.446041+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3M6Y2IESZ23","created_at":"2026-07-05T01:34:11.446041+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3M6Y2IESZ23S36S","created_at":"2026-07-05T01:34:11.446041+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3M6Y2IE","created_at":"2026-07-05T01:34:11.446041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18780","citing_title":"Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3","json":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3.json","graph_json":"https://pith.science/api/pith-number/G3M6Y2IESZ23S36SRANHRNJKK3/graph.json","events_json":"https://pith.science/api/pith-number/G3M6Y2IESZ23S36SRANHRNJKK3/events.json","paper":"https://pith.science/paper/G3M6Y2IE"},"agent_actions":{"view_html":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3","download_json":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3.json","view_paper":"https://pith.science/paper/G3M6Y2IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02976&json=true","fetch_graph":"https://pith.science/api/pith-number/G3M6Y2IESZ23S36SRANHRNJKK3/graph.json","fetch_events":"https://pith.science/api/pith-number/G3M6Y2IESZ23S36SRANHRNJKK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3/action/storage_attestation","attest_author":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3/action/author_attestation","sign_citation":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3/action/citation_signature","submit_replication":"https://pith.science/pith/G3M6Y2IESZ23S36SRANHRNJKK3/action/replication_record"}},"created_at":"2026-07-05T01:34:11.446041+00:00","updated_at":"2026-07-05T01:34:11.446041+00:00"}