{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YFMYQMUOFJTL56GOVJGBX7C5OA","short_pith_number":"pith:YFMYQMUO","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"},"canonical_sha256":"c15988328e2a66bef8ceaa4c1bfc5d701511471350bb965eb142e809669d4984","source":{"kind":"arxiv","id":"1804.11225","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11225","created_at":"2026-05-18T00:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11225v2","created_at":"2026-05-18T00:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11225","created_at":"2026-05-18T00:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"YFMYQMUOFJTL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YFMYQMUOFJTL56GO","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YFMYQMUO","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YFMYQMUOFJTL56GOVJGBX7C5OA","target":"record","payload":{"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"},"canonical_sha256":"c15988328e2a66bef8ceaa4c1bfc5d701511471350bb965eb142e809669d4984","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"},"source_kind":"arxiv","source_id":"1804.11225","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qtJ6BQWDxWnOrP+skIwn2sWpwAwv/taOyf9ohC9eEVM3U1NltNQDPGT8PgitWHjswttbtq39ZPJvjJgL2MhDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:30:28.906373Z"},"content_sha256":"bc6e9dcd00ff69d6abe1c290ed592027610310c3715543d39184d41310633004","schema_version":"1.0","event_id":"sha256:bc6e9dcd00ff69d6abe1c290ed592027610310c3715543d39184d41310633004"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YFMYQMUOFJTL56GOVJGBX7C5OA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a36jIpvcz8X84vKrDTbObtKRfAdUr9Oqrpe6IEXKYAQacWph39g0AMWpbsl0N2N9Y4Ui/9L829SeFXOzTlMMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:30:28.906942Z"},"content_sha256":"1667f67ffed09d86875f291817aa29a7d9b40dc967704464207f51f1416d185d","schema_version":"1.0","event_id":"sha256:1667f67ffed09d86875f291817aa29a7d9b40dc967704464207f51f1416d185d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/bundle.json","state_url":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T20:30:28Z","links":{"resolver":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA","bundle":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/bundle.json","state":"https://pith.science/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFMYQMUOFJTL56GOVJGBX7C5OA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YFMYQMUOFJTL56GOVJGBX7C5OA","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":"418026004fb91df48df628ded63f98bfa6d2393e1871b8e93a2e3073a73ebccd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T14:17:36Z","title_canon_sha256":"d53d5c3b24fdeb38c2b713568af0ec3f76bd746c11d351b87994b4cf7affe746"},"schema_version":"1.0","source":{"id":"1804.11225","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11225","created_at":"2026-05-18T00:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11225v2","created_at":"2026-05-18T00:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11225","created_at":"2026-05-18T00:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"YFMYQMUOFJTL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YFMYQMUOFJTL56GO","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YFMYQMUO","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:1667f67ffed09d86875f291817aa29a7d9b40dc967704464207f51f1416d185d","target":"graph","created_at":"2026-05-18T00:16:41Z","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"},"paper":{"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","authors_text":"Leshem Choshen, Omri Abend","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T14:17:36Z","title":"Automatic Metric Validation for Grammatical Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11225","kind":"arxiv","version":2},"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:bc6e9dcd00ff69d6abe1c290ed592027610310c3715543d39184d41310633004","target":"record","created_at":"2026-05-18T00:16:41Z","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":"418026004fb91df48df628ded63f98bfa6d2393e1871b8e93a2e3073a73ebccd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T14:17:36Z","title_canon_sha256":"d53d5c3b24fdeb38c2b713568af0ec3f76bd746c11d351b87994b4cf7affe746"},"schema_version":"1.0","source":{"id":"1804.11225","kind":"arxiv","version":2}},"canonical_sha256":"c15988328e2a66bef8ceaa4c1bfc5d701511471350bb965eb142e809669d4984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c15988328e2a66bef8ceaa4c1bfc5d701511471350bb965eb142e809669d4984","first_computed_at":"2026-05-18T00:16:41.778379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:41.778379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aIjRbtNc41SkoJOakc2TgCYA+uwLitGYL+0Hd4VxebFf6kC4Lfb9bsM71emxO79HnBy6QEhyHi+7H6cuqd5BDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:41.779022Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.11225","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc6e9dcd00ff69d6abe1c290ed592027610310c3715543d39184d41310633004","sha256:1667f67ffed09d86875f291817aa29a7d9b40dc967704464207f51f1416d185d"],"state_sha256":"62ae78d001caeb22a86ea02628cc8708eeb415c89fe073420f31355f61525511"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKOKGnD6YEerS3e4VmsUyBCT+Ave6L03nPOX73bbxXS+taMCUwGOnbG0SGb/qQursgT69n62yzdWZK+BokI0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:30:28.910356Z","bundle_sha256":"25dab0bb1eb5404b5b9432e467bf0117153cf5bf232f4ade557560c5ff2765f5"}}