{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T46GXTRNLT3BSIDNCGZRKQHFF3","short_pith_number":"pith:T46GXTRN","schema_version":"1.0","canonical_sha256":"9f3c6bce2d5cf619206d11b31540e52ecbbbb87c2f7733959a7111bc3a969911","source":{"kind":"arxiv","id":"2010.05700","version":1},"attestation_state":"computed","paper":{"title":"Reformulating Unsupervised Style Transfer as Paraphrase Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Kalpesh Krishna, Mohit Iyyer","submitted_at":"2020-10-12T13:31:01Z","abstract_excerpt":"Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However, many existing systems purportedly designed for style transfer inherently warp the input's meaning through attribute transfer, which changes semantic properties such as sentiment. In this paper, we reformulate unsupervised style transfer as a paraphrase generation problem, and present a simple methodology based on fine-tuning pretrained language models on autom"},"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":"2010.05700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T13:31:01Z","cross_cats_sorted":[],"title_canon_sha256":"fc3627c8dcad849023d575f372a4fb348214fa31beef5c92abac3b3848196f03","abstract_canon_sha256":"f3843cda600705dddaae6a7915fdb610741462e47f0ae1dbce96a8a642450865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:09.713540Z","signature_b64":"YytZcXBDCj9v9wAqUVc6txbu68vsM16yrlX/87B9inl+We/ApCyINXt9tERuoqubtHYNP6EofOCbCTHfpvAsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f3c6bce2d5cf619206d11b31540e52ecbbbb87c2f7733959a7111bc3a969911","last_reissued_at":"2026-07-05T01:42:09.713109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:09.713109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reformulating Unsupervised Style Transfer as Paraphrase Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Kalpesh Krishna, Mohit Iyyer","submitted_at":"2020-10-12T13:31:01Z","abstract_excerpt":"Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However, many existing systems purportedly designed for style transfer inherently warp the input's meaning through attribute transfer, which changes semantic properties such as sentiment. In this paper, we reformulate unsupervised style transfer as a paraphrase generation problem, and present a simple methodology based on fine-tuning pretrained language models on autom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05700","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/2010.05700/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":"2010.05700","created_at":"2026-07-05T01:42:09.713164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.05700v1","created_at":"2026-07-05T01:42:09.713164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05700","created_at":"2026-07-05T01:42:09.713164+00:00"},{"alias_kind":"pith_short_12","alias_value":"T46GXTRNLT3B","created_at":"2026-07-05T01:42:09.713164+00:00"},{"alias_kind":"pith_short_16","alias_value":"T46GXTRNLT3BSIDN","created_at":"2026-07-05T01:42:09.713164+00:00"},{"alias_kind":"pith_short_8","alias_value":"T46GXTRN","created_at":"2026-07-05T01:42:09.713164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00009","citing_title":"Controllable Narrative Rendering for Enhanced Assisted Writing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14513","citing_title":"PeerPrism: Peer Evaluation Expertise vs Review-writing AI","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3","json":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3.json","graph_json":"https://pith.science/api/pith-number/T46GXTRNLT3BSIDNCGZRKQHFF3/graph.json","events_json":"https://pith.science/api/pith-number/T46GXTRNLT3BSIDNCGZRKQHFF3/events.json","paper":"https://pith.science/paper/T46GXTRN"},"agent_actions":{"view_html":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3","download_json":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3.json","view_paper":"https://pith.science/paper/T46GXTRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.05700&json=true","fetch_graph":"https://pith.science/api/pith-number/T46GXTRNLT3BSIDNCGZRKQHFF3/graph.json","fetch_events":"https://pith.science/api/pith-number/T46GXTRNLT3BSIDNCGZRKQHFF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3/action/storage_attestation","attest_author":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3/action/author_attestation","sign_citation":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3/action/citation_signature","submit_replication":"https://pith.science/pith/T46GXTRNLT3BSIDNCGZRKQHFF3/action/replication_record"}},"created_at":"2026-07-05T01:42:09.713164+00:00","updated_at":"2026-07-05T01:42:09.713164+00:00"}