{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3J2RFDN2A3TFXJC77OZOFK6MF5","short_pith_number":"pith:3J2RFDN2","schema_version":"1.0","canonical_sha256":"da75128dba06e65ba45ffbb2e2abcc2f4611ea6ab08c9360bee92d1519db634e","source":{"kind":"arxiv","id":"2403.01106","version":2},"attestation_state":"computed","paper":{"title":"Distilling Text Style Transfer With Self-Explanation From LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Honglong Cai, Le Hou, Muhammad Abdul-Mageed, Yuexin Wu, Yuezhang (Music) Li","submitted_at":"2024-03-02T06:38:15Z","abstract_excerpt":"Text Style Transfer (TST) seeks to alter the style of text while retaining its core content. Given the constraints of limited parallel datasets for TST, we propose CoTeX, a framework that leverages large language models (LLMs) alongside chain-of-thought (CoT) prompting to facilitate TST. CoTeX distills the complex rewriting and reasoning capabilities of LLMs into more streamlined models capable of working with both non-parallel and parallel data. Through experimentation across four TST datasets, CoTeX is shown to surpass traditional supervised fine-tuning and knowledge distillation methods, pa"},"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":"2403.01106","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T06:38:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7177051651ba56508de0026903e8bbc75125d51d34ab8797669eed79142281af","abstract_canon_sha256":"d47ae56e21f5cf6946d776a54e455446da4d3e6753573d74918b5e8e8aa40c02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:45.965247Z","signature_b64":"n+fcHT3p3Lcm0DFvF7seFsktA/dF2MPu1UoLQY52JuK+ZUSI3w3nlHZQQsYcM3I+vix84QSWsrta4+gpfSpzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da75128dba06e65ba45ffbb2e2abcc2f4611ea6ab08c9360bee92d1519db634e","last_reissued_at":"2026-07-05T08:15:45.964846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:45.964846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Text Style Transfer With Self-Explanation From LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Honglong Cai, Le Hou, Muhammad Abdul-Mageed, Yuexin Wu, Yuezhang (Music) Li","submitted_at":"2024-03-02T06:38:15Z","abstract_excerpt":"Text Style Transfer (TST) seeks to alter the style of text while retaining its core content. Given the constraints of limited parallel datasets for TST, we propose CoTeX, a framework that leverages large language models (LLMs) alongside chain-of-thought (CoT) prompting to facilitate TST. CoTeX distills the complex rewriting and reasoning capabilities of LLMs into more streamlined models capable of working with both non-parallel and parallel data. Through experimentation across four TST datasets, CoTeX is shown to surpass traditional supervised fine-tuning and knowledge distillation methods, pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01106","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.01106/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":"2403.01106","created_at":"2026-07-05T08:15:45.964896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01106v2","created_at":"2026-07-05T08:15:45.964896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01106","created_at":"2026-07-05T08:15:45.964896+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J2RFDN2A3TF","created_at":"2026-07-05T08:15:45.964896+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J2RFDN2A3TFXJC7","created_at":"2026-07-05T08:15:45.964896+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J2RFDN2","created_at":"2026-07-05T08:15:45.964896+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/3J2RFDN2A3TFXJC77OZOFK6MF5","json":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5.json","graph_json":"https://pith.science/api/pith-number/3J2RFDN2A3TFXJC77OZOFK6MF5/graph.json","events_json":"https://pith.science/api/pith-number/3J2RFDN2A3TFXJC77OZOFK6MF5/events.json","paper":"https://pith.science/paper/3J2RFDN2"},"agent_actions":{"view_html":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5","download_json":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5.json","view_paper":"https://pith.science/paper/3J2RFDN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01106&json=true","fetch_graph":"https://pith.science/api/pith-number/3J2RFDN2A3TFXJC77OZOFK6MF5/graph.json","fetch_events":"https://pith.science/api/pith-number/3J2RFDN2A3TFXJC77OZOFK6MF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5/action/storage_attestation","attest_author":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5/action/author_attestation","sign_citation":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5/action/citation_signature","submit_replication":"https://pith.science/pith/3J2RFDN2A3TFXJC77OZOFK6MF5/action/replication_record"}},"created_at":"2026-07-05T08:15:45.964896+00:00","updated_at":"2026-07-05T08:15:45.964896+00:00"}