{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4Y3SGHXJBBPDMQ2DLGCKXZKM3F","short_pith_number":"pith:4Y3SGHXJ","canonical_record":{"source":{"id":"1903.00138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T03:08:03Z","cross_cats_sorted":[],"title_canon_sha256":"3d6f331ada8251cc0b5058ba3c584c2f92dd1fd1668a1fa26056caca04f50915","abstract_canon_sha256":"319c5cd156b49231f8e3246f074a5aadc3a9dc4beddc9daea4aa53c62cbe2634"},"schema_version":"1.0"},"canonical_sha256":"e637231ee9085e3643435984abe54cd968ff8378d085cb0087e6adc7139b3ab8","source":{"kind":"arxiv","id":"1903.00138","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00138","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00138v3","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00138","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"4Y3SGHXJBBPD","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4Y3SGHXJBBPDMQ2D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4Y3SGHXJ","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4Y3SGHXJBBPDMQ2DLGCKXZKM3F","target":"record","payload":{"canonical_record":{"source":{"id":"1903.00138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T03:08:03Z","cross_cats_sorted":[],"title_canon_sha256":"3d6f331ada8251cc0b5058ba3c584c2f92dd1fd1668a1fa26056caca04f50915","abstract_canon_sha256":"319c5cd156b49231f8e3246f074a5aadc3a9dc4beddc9daea4aa53c62cbe2634"},"schema_version":"1.0"},"canonical_sha256":"e637231ee9085e3643435984abe54cd968ff8378d085cb0087e6adc7139b3ab8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:42.523781Z","signature_b64":"JV/XBhGK1sZ/D07jo3y5nBtFNWmUvI1fFTKp+xDJw/unrOH7g/3IunacJOUpi2pwTzp16WXtczQVfd4DBnTVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e637231ee9085e3643435984abe54cd968ff8378d085cb0087e6adc7139b3ab8","last_reissued_at":"2026-05-17T23:43:42.523051Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:42.523051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.00138","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHX0tUzVs2G8IHQoXC7ngjvTR8teD4Ks2X4NPZev7ZSmUUvo5WoiprSa5pjwOf4qFQ435PXDmLGzoFWDiXt4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:50:13.808461Z"},"content_sha256":"10bb3e66487b86dd0cce5b42ddf779aae885e789bd3543ff78d89d74c951926e","schema_version":"1.0","event_id":"sha256:10bb3e66487b86dd0cce5b42ddf779aae885e789bd3543ff78d89d74c951926e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4Y3SGHXJBBPDMQ2DLGCKXZKM3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingming Liu, Kewei Shen, Liang Wang, Ruoyu Jia, Wei Zhao","submitted_at":"2019-03-01T03:08:03Z","abstract_excerpt":"Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task. In this paper, we propose a copy-augmented architecture for the GEC task by copying the unchanged words from the source sentence to the target sentence. Since the GEC suffers from not having enough labeled training data to achieve high accuracy. We pre-train the copy-augmented architecture with a denoising auto-encoder using the unlabeled One Billion Benchmark and make comparisons between the fully pre-trained model and a partially pre-trained model. It is the first time copy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00138","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":""},"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":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xbpfm4LAKmgAWiLG4Q84VL8IglWF1JDWkqeCrbkpfkpCyLCVfxWg8SncIkontLLnWPmD2FlKLJtdbshxnferDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:50:13.809074Z"},"content_sha256":"9ad7be34740789584a47964cbcbf7633c7def6f9b195712a7837227f9c27c0fd","schema_version":"1.0","event_id":"sha256:9ad7be34740789584a47964cbcbf7633c7def6f9b195712a7837227f9c27c0fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F/bundle.json","state_url":"https://pith.science/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F/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":"2026-06-01T05:50:13Z","links":{"resolver":"https://pith.science/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F","bundle":"https://pith.science/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F/bundle.json","state":"https://pith.science/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4Y3SGHXJBBPDMQ2DLGCKXZKM3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4Y3SGHXJBBPDMQ2DLGCKXZKM3F","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":"319c5cd156b49231f8e3246f074a5aadc3a9dc4beddc9daea4aa53c62cbe2634","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T03:08:03Z","title_canon_sha256":"3d6f331ada8251cc0b5058ba3c584c2f92dd1fd1668a1fa26056caca04f50915"},"schema_version":"1.0","source":{"id":"1903.00138","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00138","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00138v3","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00138","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"4Y3SGHXJBBPD","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4Y3SGHXJBBPDMQ2D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4Y3SGHXJ","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:9ad7be34740789584a47964cbcbf7633c7def6f9b195712a7837227f9c27c0fd","target":"graph","created_at":"2026-05-17T23:43:42Z","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":"Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task. In this paper, we propose a copy-augmented architecture for the GEC task by copying the unchanged words from the source sentence to the target sentence. Since the GEC suffers from not having enough labeled training data to achieve high accuracy. We pre-train the copy-augmented architecture with a denoising auto-encoder using the unlabeled One Billion Benchmark and make comparisons between the fully pre-trained model and a partially pre-trained model. It is the first time copy","authors_text":"Jingming Liu, Kewei Shen, Liang Wang, Ruoyu Jia, Wei Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T03:08:03Z","title":"Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00138","kind":"arxiv","version":3},"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":"sha256:10bb3e66487b86dd0cce5b42ddf779aae885e789bd3543ff78d89d74c951926e","target":"record","created_at":"2026-05-17T23:43:42Z","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":"319c5cd156b49231f8e3246f074a5aadc3a9dc4beddc9daea4aa53c62cbe2634","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T03:08:03Z","title_canon_sha256":"3d6f331ada8251cc0b5058ba3c584c2f92dd1fd1668a1fa26056caca04f50915"},"schema_version":"1.0","source":{"id":"1903.00138","kind":"arxiv","version":3}},"canonical_sha256":"e637231ee9085e3643435984abe54cd968ff8378d085cb0087e6adc7139b3ab8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e637231ee9085e3643435984abe54cd968ff8378d085cb0087e6adc7139b3ab8","first_computed_at":"2026-05-17T23:43:42.523051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:42.523051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JV/XBhGK1sZ/D07jo3y5nBtFNWmUvI1fFTKp+xDJw/unrOH7g/3IunacJOUpi2pwTzp16WXtczQVfd4DBnTVBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:42.523781Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00138","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10bb3e66487b86dd0cce5b42ddf779aae885e789bd3543ff78d89d74c951926e","sha256:9ad7be34740789584a47964cbcbf7633c7def6f9b195712a7837227f9c27c0fd"],"state_sha256":"932ec8e6819a1ebda60eaa558c3cecd6b94bb9eee72214b1b39be027f4933b40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vd1kmxKhvqV6ZLolQnC8bphaPyKh+6xIkPx+GFP3Xk+m7T6cSDgE5tyrSYX+eYm5OR/dqhHRq/Cg/9maF/WlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:50:13.812274Z","bundle_sha256":"ea37561def59c322185116a0edb59c3d61f906df8885f65b8fbaab0b207fa278"}}