{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QREPWTX4TA6KN7ZJQCG5M72QSS","short_pith_number":"pith:QREPWTX4","schema_version":"1.0","canonical_sha256":"8448fb4efc983ca6ff29808dd67f5094befc9f982ce9b9223d27f3fb3654b69f","source":{"kind":"arxiv","id":"1707.09067","version":1},"attestation_state":"computed","paper":{"title":"Adapting Sequence Models for Sentence Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Allen Schmaltz, Stuart M. Shieber, Yoon Kim","submitted_at":"2017-07-27T22:50:55Z","abstract_excerpt":"In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard approaches. Our strongest sequence-to-sequence model improves over our strongest phrase-based statistical machine translation model, with access to the same data, by 6 M2 (0.5 GLEU) points. Additionally, in the data environment of the standard CoNLL-2014 setup"},"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":"1707.09067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-27T22:50:55Z","cross_cats_sorted":[],"title_canon_sha256":"3e8702f88ab0ff3525bb9a4c01731b38f41bdfa03987f84c195b6c052d88b210","abstract_canon_sha256":"00633c4cefa927973a5b06f63b91dcebfb147ad8bc321571fe47c30bf0b5652b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:17.203618Z","signature_b64":"yuSLkXv4KNbAZWs1lIv2bk5ABy3mTaMCmrYChrKh0ue3uudV0NmyVvp8UewlFYI80ulkmF8B/DkbElxdhu6eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8448fb4efc983ca6ff29808dd67f5094befc9f982ce9b9223d27f3fb3654b69f","last_reissued_at":"2026-05-18T00:39:17.202941Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:17.202941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Sequence Models for Sentence Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Allen Schmaltz, Stuart M. Shieber, Yoon Kim","submitted_at":"2017-07-27T22:50:55Z","abstract_excerpt":"In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard approaches. Our strongest sequence-to-sequence model improves over our strongest phrase-based statistical machine translation model, with access to the same data, by 6 M2 (0.5 GLEU) points. Additionally, in the data environment of the standard CoNLL-2014 setup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09067","kind":"arxiv","version":1},"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":"1707.09067","created_at":"2026-05-18T00:39:17.203062+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09067v1","created_at":"2026-05-18T00:39:17.203062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09067","created_at":"2026-05-18T00:39:17.203062+00:00"},{"alias_kind":"pith_short_12","alias_value":"QREPWTX4TA6K","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QREPWTX4TA6KN7ZJ","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QREPWTX4","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10907","citing_title":"Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS","json":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS.json","graph_json":"https://pith.science/api/pith-number/QREPWTX4TA6KN7ZJQCG5M72QSS/graph.json","events_json":"https://pith.science/api/pith-number/QREPWTX4TA6KN7ZJQCG5M72QSS/events.json","paper":"https://pith.science/paper/QREPWTX4"},"agent_actions":{"view_html":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS","download_json":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS.json","view_paper":"https://pith.science/paper/QREPWTX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09067&json=true","fetch_graph":"https://pith.science/api/pith-number/QREPWTX4TA6KN7ZJQCG5M72QSS/graph.json","fetch_events":"https://pith.science/api/pith-number/QREPWTX4TA6KN7ZJQCG5M72QSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS/action/storage_attestation","attest_author":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS/action/author_attestation","sign_citation":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS/action/citation_signature","submit_replication":"https://pith.science/pith/QREPWTX4TA6KN7ZJQCG5M72QSS/action/replication_record"}},"created_at":"2026-05-18T00:39:17.203062+00:00","updated_at":"2026-05-18T00:39:17.203062+00:00"}