{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PZHS6ZHPFIWF3YC3F3OYGSJINM","short_pith_number":"pith:PZHS6ZHP","schema_version":"1.0","canonical_sha256":"7e4f2f64ef2a2c5de05b2edd8349286b193214ad5b78c52aef5a7f2dfe08eef4","source":{"kind":"arxiv","id":"1711.05732","version":2},"attestation_state":"computed","paper":{"title":"ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Kevin Gimpel","submitted_at":"2017-11-15T18:59:29Z","abstract_excerpt":"We describe PARANMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs. We generated the pairs automatically by using neural machine translation to translate the non-English side of a large parallel corpus, following Wieting et al. (2017). Our hope is that ParaNMT-50M can be a valuable resource for paraphrase generation and can provide a rich source of semantic knowledge to improve downstream natural language understanding tasks. To show its utility, we use ParaNMT-50M to train paraphrastic sentence embeddings that outperform all supervised systems on every SemE"},"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":"1711.05732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-15T18:59:29Z","cross_cats_sorted":[],"title_canon_sha256":"96ca8e94d4f9256b302f580d29667ba842d616515be4924d1b5a76ac33481615","abstract_canon_sha256":"422d795d79c8a47707ad3f76c9e8de74e861060498ac9bf7d2b3c9f9e35ecb8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:59.863463Z","signature_b64":"Zvy2TrVZahjcRkHh4p03l0+5FKTwiiShO1MNUirYhyZcY/wHzPOMC4QMfnh3nxYUFBTmfwhRxhu15zWs9al8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e4f2f64ef2a2c5de05b2edd8349286b193214ad5b78c52aef5a7f2dfe08eef4","last_reissued_at":"2026-05-18T00:17:59.862753Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:59.862753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Kevin Gimpel","submitted_at":"2017-11-15T18:59:29Z","abstract_excerpt":"We describe PARANMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs. We generated the pairs automatically by using neural machine translation to translate the non-English side of a large parallel corpus, following Wieting et al. (2017). Our hope is that ParaNMT-50M can be a valuable resource for paraphrase generation and can provide a rich source of semantic knowledge to improve downstream natural language understanding tasks. To show its utility, we use ParaNMT-50M to train paraphrastic sentence embeddings that outperform all supervised systems on every SemE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05732","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":"1711.05732","created_at":"2026-05-18T00:17:59.862841+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.05732v2","created_at":"2026-05-18T00:17:59.862841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05732","created_at":"2026-05-18T00:17:59.862841+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZHS6ZHPFIWF","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZHS6ZHPFIWF3YC3","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZHS6ZHP","created_at":"2026-05-18T12:31:37.085036+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/PZHS6ZHPFIWF3YC3F3OYGSJINM","json":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM.json","graph_json":"https://pith.science/api/pith-number/PZHS6ZHPFIWF3YC3F3OYGSJINM/graph.json","events_json":"https://pith.science/api/pith-number/PZHS6ZHPFIWF3YC3F3OYGSJINM/events.json","paper":"https://pith.science/paper/PZHS6ZHP"},"agent_actions":{"view_html":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM","download_json":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM.json","view_paper":"https://pith.science/paper/PZHS6ZHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.05732&json=true","fetch_graph":"https://pith.science/api/pith-number/PZHS6ZHPFIWF3YC3F3OYGSJINM/graph.json","fetch_events":"https://pith.science/api/pith-number/PZHS6ZHPFIWF3YC3F3OYGSJINM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM/action/storage_attestation","attest_author":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM/action/author_attestation","sign_citation":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM/action/citation_signature","submit_replication":"https://pith.science/pith/PZHS6ZHPFIWF3YC3F3OYGSJINM/action/replication_record"}},"created_at":"2026-05-18T00:17:59.862841+00:00","updated_at":"2026-05-18T00:17:59.862841+00:00"}