{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I5Y2GP6RRMHM2VDJEPJIRB3OLM","short_pith_number":"pith:I5Y2GP6R","schema_version":"1.0","canonical_sha256":"4771a33fd18b0ecd546923d288876e5b0ea17f4b00eab9ffb8c471d60c1182d0","source":{"kind":"arxiv","id":"2112.03154","version":1},"attestation_state":"computed","paper":{"title":"VAE based Text Style Transfer with Pivot Words Enhancement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengyuan Ma, Chenlei Guo, Haoran Xu, Sixing Lu, Zhongkai Sun","submitted_at":"2021-12-06T16:41:26Z","abstract_excerpt":"Text Style Transfer (TST) aims to alter the underlying style of the source text to another specific style while keeping the same content. Due to the scarcity of high-quality parallel training data, unsupervised learning has become a trending direction for TST tasks. In this paper, we propose a novel VAE based Text Style Transfer with pivOt Words Enhancement leaRning (VT-STOWER) method which utilizes Variational AutoEncoder (VAE) and external style embeddings to learn semantics and style distribution jointly. Additionally, we introduce pivot words learning, which is applied to learn decisive wo"},"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":"2112.03154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-06T16:41:26Z","cross_cats_sorted":[],"title_canon_sha256":"e7d723b2828d3e7c3ff742c16876d14e123581b0a81714d954f0c8aa13f380b7","abstract_canon_sha256":"700a4bc22068a17c3b5f20e8f2ca5ba3c266e938ad9ad04dc59ed8edb0bba618"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:02.745364Z","signature_b64":"6f6dqtRkTuO6AY9Xo3q/u18Dc6f0wa0n8M2BmIT5bhuQlpypuIAEMxFDwfEOxFh4bDU8LMSu6ogDNQxabd+bAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4771a33fd18b0ecd546923d288876e5b0ea17f4b00eab9ffb8c471d60c1182d0","last_reissued_at":"2026-07-05T03:38:02.744944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:02.744944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAE based Text Style Transfer with Pivot Words Enhancement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengyuan Ma, Chenlei Guo, Haoran Xu, Sixing Lu, Zhongkai Sun","submitted_at":"2021-12-06T16:41:26Z","abstract_excerpt":"Text Style Transfer (TST) aims to alter the underlying style of the source text to another specific style while keeping the same content. Due to the scarcity of high-quality parallel training data, unsupervised learning has become a trending direction for TST tasks. In this paper, we propose a novel VAE based Text Style Transfer with pivOt Words Enhancement leaRning (VT-STOWER) method which utilizes Variational AutoEncoder (VAE) and external style embeddings to learn semantics and style distribution jointly. Additionally, we introduce pivot words learning, which is applied to learn decisive wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03154","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/2112.03154/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":"2112.03154","created_at":"2026-07-05T03:38:02.744998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03154v1","created_at":"2026-07-05T03:38:02.744998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03154","created_at":"2026-07-05T03:38:02.744998+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5Y2GP6RRMHM","created_at":"2026-07-05T03:38:02.744998+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5Y2GP6RRMHM2VDJ","created_at":"2026-07-05T03:38:02.744998+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5Y2GP6R","created_at":"2026-07-05T03:38:02.744998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08071","citing_title":"COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM","json":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM.json","graph_json":"https://pith.science/api/pith-number/I5Y2GP6RRMHM2VDJEPJIRB3OLM/graph.json","events_json":"https://pith.science/api/pith-number/I5Y2GP6RRMHM2VDJEPJIRB3OLM/events.json","paper":"https://pith.science/paper/I5Y2GP6R"},"agent_actions":{"view_html":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM","download_json":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM.json","view_paper":"https://pith.science/paper/I5Y2GP6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03154&json=true","fetch_graph":"https://pith.science/api/pith-number/I5Y2GP6RRMHM2VDJEPJIRB3OLM/graph.json","fetch_events":"https://pith.science/api/pith-number/I5Y2GP6RRMHM2VDJEPJIRB3OLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM/action/storage_attestation","attest_author":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM/action/author_attestation","sign_citation":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM/action/citation_signature","submit_replication":"https://pith.science/pith/I5Y2GP6RRMHM2VDJEPJIRB3OLM/action/replication_record"}},"created_at":"2026-07-05T03:38:02.744998+00:00","updated_at":"2026-07-05T03:38:02.744998+00:00"}