{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YFMYQMUOFJTL56GOVJGBX7C5OA","short_pith_number":"pith:YFMYQMUO","schema_version":"1.0","canonical_sha256":"c15988328e2a66bef8ceaa4c1bfc5d701511471350bb965eb142e809669d4984","source":{"kind":"arxiv","id":"1804.11225","version":2},"attestation_state":"computed","paper":{"title":"Automatic Metric Validation for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leshem Choshen, Omri Abend","submitted_at":"2018-04-30T14:17:36Z","abstract_excerpt":"Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties with existing practices. Experiments with \\maege\\ shed a new light on metric quality, showing for example that the standard $M^2$ metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analy"},"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":"1804.11225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T14:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"d53d5c3b24fdeb38c2b713568af0ec3f76bd746c11d351b87994b4cf7affe746","abstract_canon_sha256":"418026004fb91df48df628ded63f98bfa6d2393e1871b8e93a2e3073a73ebccd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:41.779022Z","signature_b64":"aIjRbtNc41SkoJOakc2TgCYA+uwLitGYL+0Hd4VxebFf6kC4Lfb9bsM71emxO79HnBy6QEhyHi+7H6cuqd5BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15988328e2a66bef8ceaa4c1bfc5d701511471350bb965eb142e809669d4984","last_reissued_at":"2026-05-18T00:16:41.778379Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:41.778379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Metric Validation for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leshem Choshen, Omri Abend","submitted_at":"2018-04-30T14:17:36Z","abstract_excerpt":"Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties with existing practices. Experiments with \\maege\\ shed a new light on metric quality, showing for example that the standard $M^2$ metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11225","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":""},"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":"1804.11225","created_at":"2026-05-18T00:16:41.778478+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.11225v2","created_at":"2026-05-18T00:16:41.778478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11225","created_at":"2026-05-18T00:16:41.778478+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFMYQMUOFJTL","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFMYQMUOFJTL56GO","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFMYQMUO","created_at":"2026-05-18T12:33:04.347982+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/YFMYQMUOFJTL56GOVJGBX7C5OA","json":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA.json","graph_json":"https://pith.science/api/pith-number/YFMYQMUOFJTL56GOVJGBX7C5OA/graph.json","events_json":"https://pith.science/api/pith-number/YFMYQMUOFJTL56GOVJGBX7C5OA/events.json","paper":"https://pith.science/paper/YFMYQMUO"},"agent_actions":{"view_html":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA","download_json":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA.json","view_paper":"https://pith.science/paper/YFMYQMUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.11225&json=true","fetch_graph":"https://pith.science/api/pith-number/YFMYQMUOFJTL56GOVJGBX7C5OA/graph.json","fetch_events":"https://pith.science/api/pith-number/YFMYQMUOFJTL56GOVJGBX7C5OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/action/storage_attestation","attest_author":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/action/author_attestation","sign_citation":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/action/citation_signature","submit_replication":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/action/replication_record"}},"created_at":"2026-05-18T00:16:41.778478+00:00","updated_at":"2026-05-18T00:16:41.778478+00:00"}