{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LYUARCIW6I4BCLAOVB3P5DI5F2","short_pith_number":"pith:LYUARCIW","schema_version":"1.0","canonical_sha256":"5e28088916f238112c0ea876fe8d1d2e9beba57bcbc2bae5e34af2887da430f9","source":{"kind":"arxiv","id":"1911.03597","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Paraphrase Generation with Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qing Zhang, Qun Liu, Xin Jiang, Yibo Zhang, Yi Liao, Yinpeng Guo","submitted_at":"2019-11-09T02:49:31Z","abstract_excerpt":"Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to this end. However, we notice that the pivoting process involves multiple machine translation models and is likely to incur semantic drift during the two-step translations. In this paper, inspired by the Transformer-based language models, we propose a simple and unified paraphrasing model, which is purely trained on multilingual parallel data and can conduct "},"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":"1911.03597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-09T02:49:31Z","cross_cats_sorted":[],"title_canon_sha256":"57daa26f2599f2c339aed998335e4f6adfe09b2c2f5d7d157d594777743b470b","abstract_canon_sha256":"1c4aee7b8dea951255edc6590b4e80f3e69f093ce4fc20f037889954dc8f282c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:14.009978Z","signature_b64":"N64aXR0IOL2U0Z74SSBOm90Y5wjo7ZEuZMTxbzuRPjTcEIaQfW6MF7ArJVtC6FP1JxzByTN5jhSohE36LT1wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e28088916f238112c0ea876fe8d1d2e9beba57bcbc2bae5e34af2887da430f9","last_reissued_at":"2026-07-05T00:18:14.009523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:14.009523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Paraphrase Generation with Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qing Zhang, Qun Liu, Xin Jiang, Yibo Zhang, Yi Liao, Yinpeng Guo","submitted_at":"2019-11-09T02:49:31Z","abstract_excerpt":"Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to this end. However, we notice that the pivoting process involves multiple machine translation models and is likely to incur semantic drift during the two-step translations. In this paper, inspired by the Transformer-based language models, we propose a simple and unified paraphrasing model, which is purely trained on multilingual parallel data and can conduct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03597","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.03597/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1911.03597","created_at":"2026-07-05T00:18:14.009579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03597v1","created_at":"2026-07-05T00:18:14.009579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03597","created_at":"2026-07-05T00:18:14.009579+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYUARCIW6I4B","created_at":"2026-07-05T00:18:14.009579+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYUARCIW6I4BCLAO","created_at":"2026-07-05T00:18:14.009579+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYUARCIW","created_at":"2026-07-05T00:18:14.009579+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/LYUARCIW6I4BCLAOVB3P5DI5F2","json":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2.json","graph_json":"https://pith.science/api/pith-number/LYUARCIW6I4BCLAOVB3P5DI5F2/graph.json","events_json":"https://pith.science/api/pith-number/LYUARCIW6I4BCLAOVB3P5DI5F2/events.json","paper":"https://pith.science/paper/LYUARCIW"},"agent_actions":{"view_html":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2","download_json":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2.json","view_paper":"https://pith.science/paper/LYUARCIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03597&json=true","fetch_graph":"https://pith.science/api/pith-number/LYUARCIW6I4BCLAOVB3P5DI5F2/graph.json","fetch_events":"https://pith.science/api/pith-number/LYUARCIW6I4BCLAOVB3P5DI5F2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2/action/storage_attestation","attest_author":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2/action/author_attestation","sign_citation":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2/action/citation_signature","submit_replication":"https://pith.science/pith/LYUARCIW6I4BCLAOVB3P5DI5F2/action/replication_record"}},"created_at":"2026-07-05T00:18:14.009579+00:00","updated_at":"2026-07-05T00:18:14.009579+00:00"}