{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U3QJHFZEM6SDJGZ7OR36EBH7OB","short_pith_number":"pith:U3QJHFZE","schema_version":"1.0","canonical_sha256":"a6e093972467a4349b3f7477e204ff70712829be4893730a59e7e27dda5fda5f","source":{"kind":"arxiv","id":"1905.05621","version":3},"attestation_state":"computed","paper":{"title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianze Liang, Ning Dai, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-05-14T14:03:21Z","abstract_excerpt":"Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from the semantics for a sentence. 2) The recurrent neural network (RNN) based encoder and decoder, mediated by the latent representation, cannot well deal with the issue of the long-term dependency, resulting in poor preservation of non-stylistic semantic content. In this paper, we propose the Style Transformer, which makes no assumption about the latent represent"},"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":"1905.05621","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T14:03:21Z","cross_cats_sorted":[],"title_canon_sha256":"d98695f7058204cd04886964ee686bc421d3862788e3f34360f0c03386391cc7","abstract_canon_sha256":"58bc052d76b4be9093815b149dd1f0326bcaa25e8ad0c6bc9ee2a0e39867c6e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:26.795003Z","signature_b64":"BbJXu0EepZriybi8Zqmg+ji/9vpFiqqxB9C5g5JjtsomPABCV45eDe/fQA7IzdWl0azOx616DxE90ym5NlTYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6e093972467a4349b3f7477e204ff70712829be4893730a59e7e27dda5fda5f","last_reissued_at":"2026-07-04T23:58:26.794562Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:26.794562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianze Liang, Ning Dai, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-05-14T14:03:21Z","abstract_excerpt":"Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from the semantics for a sentence. 2) The recurrent neural network (RNN) based encoder and decoder, mediated by the latent representation, cannot well deal with the issue of the long-term dependency, resulting in poor preservation of non-stylistic semantic content. In this paper, we propose the Style Transformer, which makes no assumption about the latent represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05621","kind":"arxiv","version":3},"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/1905.05621/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":"1905.05621","created_at":"2026-07-04T23:58:26.794625+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05621v3","created_at":"2026-07-04T23:58:26.794625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05621","created_at":"2026-07-04T23:58:26.794625+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3QJHFZEM6SD","created_at":"2026-07-04T23:58:26.794625+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3QJHFZEM6SDJGZ7","created_at":"2026-07-04T23:58:26.794625+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3QJHFZE","created_at":"2026-07-04T23:58:26.794625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10606","citing_title":"Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB","json":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB.json","graph_json":"https://pith.science/api/pith-number/U3QJHFZEM6SDJGZ7OR36EBH7OB/graph.json","events_json":"https://pith.science/api/pith-number/U3QJHFZEM6SDJGZ7OR36EBH7OB/events.json","paper":"https://pith.science/paper/U3QJHFZE"},"agent_actions":{"view_html":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB","download_json":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB.json","view_paper":"https://pith.science/paper/U3QJHFZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05621&json=true","fetch_graph":"https://pith.science/api/pith-number/U3QJHFZEM6SDJGZ7OR36EBH7OB/graph.json","fetch_events":"https://pith.science/api/pith-number/U3QJHFZEM6SDJGZ7OR36EBH7OB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB/action/storage_attestation","attest_author":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB/action/author_attestation","sign_citation":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB/action/citation_signature","submit_replication":"https://pith.science/pith/U3QJHFZEM6SDJGZ7OR36EBH7OB/action/replication_record"}},"created_at":"2026-07-04T23:58:26.794625+00:00","updated_at":"2026-07-04T23:58:26.794625+00:00"}