{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NR74BKERRV2SBOZD57AGHSBOTO","short_pith_number":"pith:NR74BKER","schema_version":"1.0","canonical_sha256":"6c7fc0a8918d7520bb23efc063c82e9bb0cb7ac90baf38974405f0ea1d23d03c","source":{"kind":"arxiv","id":"2205.11503","version":1},"attestation_state":"computed","paper":{"title":"Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Luke Melas-Kyriazi, Mirac Suzgun","submitted_at":"2022-05-23T17:57:15Z","abstract_excerpt":"We propose a method for arbitrary textual style transfer (TST)--the task of transforming a text into any given style--utilizing general-purpose pre-trained language models. Our method, Prompt-and-Rerank, is based on a mathematical formulation of the TST task, decomposing it into three constituent components: textual similarity, target style strength, and fluency. Specifically, our method first uses zero-shot or few-shot prompting to obtain a set of candidate generations in the target style, and then re-ranks these candidates according to a combination of the three components above. Empirically"},"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":"2205.11503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"d720c259ab70bf4ef5e14f38830315d97f8640b845ae657ab8a995edbe027cd8","abstract_canon_sha256":"82a649a8b5c81bc4d377ced1e1787a54a50d40524703ac35bed353a352157bb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:37.830942Z","signature_b64":"qQj8WM4j5Oy6pKgILJ0Bh+vqrxMQerTBpG77EWwgmObY3FM+oKUeMJpYZYSmHFHiq6W23aQzNQRSWJVJsyJADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c7fc0a8918d7520bb23efc063c82e9bb0cb7ac90baf38974405f0ea1d23d03c","last_reissued_at":"2026-07-05T04:25:37.830558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:37.830558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Luke Melas-Kyriazi, Mirac Suzgun","submitted_at":"2022-05-23T17:57:15Z","abstract_excerpt":"We propose a method for arbitrary textual style transfer (TST)--the task of transforming a text into any given style--utilizing general-purpose pre-trained language models. Our method, Prompt-and-Rerank, is based on a mathematical formulation of the TST task, decomposing it into three constituent components: textual similarity, target style strength, and fluency. Specifically, our method first uses zero-shot or few-shot prompting to obtain a set of candidate generations in the target style, and then re-ranks these candidates according to a combination of the three components above. Empirically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11503","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/2205.11503/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":"2205.11503","created_at":"2026-07-05T04:25:37.830608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11503v1","created_at":"2026-07-05T04:25:37.830608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11503","created_at":"2026-07-05T04:25:37.830608+00:00"},{"alias_kind":"pith_short_12","alias_value":"NR74BKERRV2S","created_at":"2026-07-05T04:25:37.830608+00:00"},{"alias_kind":"pith_short_16","alias_value":"NR74BKERRV2SBOZD","created_at":"2026-07-05T04:25:37.830608+00:00"},{"alias_kind":"pith_short_8","alias_value":"NR74BKER","created_at":"2026-07-05T04:25:37.830608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2210.09261","citing_title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05756","citing_title":"Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO","json":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO.json","graph_json":"https://pith.science/api/pith-number/NR74BKERRV2SBOZD57AGHSBOTO/graph.json","events_json":"https://pith.science/api/pith-number/NR74BKERRV2SBOZD57AGHSBOTO/events.json","paper":"https://pith.science/paper/NR74BKER"},"agent_actions":{"view_html":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO","download_json":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO.json","view_paper":"https://pith.science/paper/NR74BKER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11503&json=true","fetch_graph":"https://pith.science/api/pith-number/NR74BKERRV2SBOZD57AGHSBOTO/graph.json","fetch_events":"https://pith.science/api/pith-number/NR74BKERRV2SBOZD57AGHSBOTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO/action/storage_attestation","attest_author":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO/action/author_attestation","sign_citation":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO/action/citation_signature","submit_replication":"https://pith.science/pith/NR74BKERRV2SBOZD57AGHSBOTO/action/replication_record"}},"created_at":"2026-07-05T04:25:37.830608+00:00","updated_at":"2026-07-05T04:25:37.830608+00:00"}