{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2RI55W4KZNCGBV3VIIWTW73FIC","short_pith_number":"pith:2RI55W4K","schema_version":"1.0","canonical_sha256":"d451dedb8acb4460d775422d3b7f654096c5e3525a216812c4c5fd2a28d4d17b","source":{"kind":"arxiv","id":"1804.11254","version":3},"attestation_state":"computed","paper":{"title":"Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leshem Choshen, Omri Abend","submitted_at":"2018-04-30T14:59:56Z","abstract_excerpt":"The prevalent use of too few references for evaluating text-to-text generation is known to bias estimates of their quality ({\\it low coverage bias} or LCB). This paper shows that overcoming LCB in Grammatical Error Correction (GEC) evaluation cannot be attained by re-scaling or by increasing the number of references in any feasible range, contrary to previous suggestions. This is due to the long-tailed distribution of valid corrections for a sentence. Concretely, we show that LCB incentivizes GEC systems to avoid correcting even when they can generate a valid correction. Consequently, existing"},"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":"1804.11254","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T14:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"2fc9e009378aef639d13deeead12cf5bea0d6408d7b21acb1585848270751621","abstract_canon_sha256":"0303d94541799d0fdc83ca7ffa9d1b1e6353f3b6c2354a14493aaa49e02f2ad9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:20.518410Z","signature_b64":"avnUwrlI1Vh1Hk6ZruF9PjF+IqeURJbduxvdpmJ+DfsgsViKsAvn1f+yR90VS+kVpnUSIw4iisyYfF7x54m+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d451dedb8acb4460d775422d3b7f654096c5e3525a216812c4c5fd2a28d4d17b","last_reissued_at":"2026-07-05T00:05:20.517782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:20.517782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leshem Choshen, Omri Abend","submitted_at":"2018-04-30T14:59:56Z","abstract_excerpt":"The prevalent use of too few references for evaluating text-to-text generation is known to bias estimates of their quality ({\\it low coverage bias} or LCB). This paper shows that overcoming LCB in Grammatical Error Correction (GEC) evaluation cannot be attained by re-scaling or by increasing the number of references in any feasible range, contrary to previous suggestions. This is due to the long-tailed distribution of valid corrections for a sentence. Concretely, we show that LCB incentivizes GEC systems to avoid correcting even when they can generate a valid correction. Consequently, existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11254","kind":"arxiv","version":3},"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/1804.11254/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":"1804.11254","created_at":"2026-07-05T00:05:20.517860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.11254v3","created_at":"2026-07-05T00:05:20.517860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11254","created_at":"2026-07-05T00:05:20.517860+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RI55W4KZNCG","created_at":"2026-07-05T00:05:20.517860+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RI55W4KZNCGBV3V","created_at":"2026-07-05T00:05:20.517860+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RI55W4K","created_at":"2026-07-05T00:05:20.517860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC","json":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC.json","graph_json":"https://pith.science/api/pith-number/2RI55W4KZNCGBV3VIIWTW73FIC/graph.json","events_json":"https://pith.science/api/pith-number/2RI55W4KZNCGBV3VIIWTW73FIC/events.json","paper":"https://pith.science/paper/2RI55W4K"},"agent_actions":{"view_html":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC","download_json":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC.json","view_paper":"https://pith.science/paper/2RI55W4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.11254&json=true","fetch_graph":"https://pith.science/api/pith-number/2RI55W4KZNCGBV3VIIWTW73FIC/graph.json","fetch_events":"https://pith.science/api/pith-number/2RI55W4KZNCGBV3VIIWTW73FIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC/action/storage_attestation","attest_author":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC/action/author_attestation","sign_citation":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC/action/citation_signature","submit_replication":"https://pith.science/pith/2RI55W4KZNCGBV3VIIWTW73FIC/action/replication_record"}},"created_at":"2026-07-05T00:05:20.517860+00:00","updated_at":"2026-07-05T00:05:20.517860+00:00"}