{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FUFVITBLV4CSLA6TU43N4AEJRO","short_pith_number":"pith:FUFVITBL","schema_version":"1.0","canonical_sha256":"2d0b544c2baf052583d3a736de00898bac2af2864c7359b05632624d42e2dfb0","source":{"kind":"arxiv","id":"2503.06781","version":1},"attestation_state":"computed","paper":{"title":"Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengrun Yang, Cong Liu, David Uthus, Ganesh Jawahar, Itai Rolnick, John Nham, Lei Shu, Yi Qiao, Yufei Li, Yun-hsuan Sung","submitted_at":"2025-03-09T21:23:52Z","abstract_excerpt":"Generic text rewriting is a prevalent large language model (LLM) application that covers diverse real-world tasks, such as style transfer, fact correction, and email editing. These tasks vary in rewriting objectives (e.g., factual consistency vs. semantic preservation), making it challenging to develop a unified model that excels across all dimensions. Existing methods often specialize in either a single task or a specific objective, limiting their generalizability. In this work, we introduce a generic model proficient in factuality, stylistic, and conversational rewriting tasks. To simulate r"},"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":"2503.06781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T21:23:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6bb22b5aa6795b58cd0e9cf2230a402c401165781bbc274941bc347cba17c125","abstract_canon_sha256":"b885d915f095c121791253a0601b54a7bc6624737377952e91430bdf7f1c6b11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:42.170727Z","signature_b64":"J5G6Kt6At88DWjbMHkG+umag1FdjN3cKeOunffkVwpETjvOMK8j9HYW9TLA0uxQh5BfrBJE97aktGU6RqqPzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d0b544c2baf052583d3a736de00898bac2af2864c7359b05632624d42e2dfb0","last_reissued_at":"2026-07-05T10:27:42.170235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:42.170235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengrun Yang, Cong Liu, David Uthus, Ganesh Jawahar, Itai Rolnick, John Nham, Lei Shu, Yi Qiao, Yufei Li, Yun-hsuan Sung","submitted_at":"2025-03-09T21:23:52Z","abstract_excerpt":"Generic text rewriting is a prevalent large language model (LLM) application that covers diverse real-world tasks, such as style transfer, fact correction, and email editing. These tasks vary in rewriting objectives (e.g., factual consistency vs. semantic preservation), making it challenging to develop a unified model that excels across all dimensions. Existing methods often specialize in either a single task or a specific objective, limiting their generalizability. In this work, we introduce a generic model proficient in factuality, stylistic, and conversational rewriting tasks. To simulate r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06781","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/2503.06781/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":"2503.06781","created_at":"2026-07-05T10:27:42.170291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06781v1","created_at":"2026-07-05T10:27:42.170291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06781","created_at":"2026-07-05T10:27:42.170291+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUFVITBLV4CS","created_at":"2026-07-05T10:27:42.170291+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUFVITBLV4CSLA6T","created_at":"2026-07-05T10:27:42.170291+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUFVITBL","created_at":"2026-07-05T10:27:42.170291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23027","citing_title":"PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO","json":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO.json","graph_json":"https://pith.science/api/pith-number/FUFVITBLV4CSLA6TU43N4AEJRO/graph.json","events_json":"https://pith.science/api/pith-number/FUFVITBLV4CSLA6TU43N4AEJRO/events.json","paper":"https://pith.science/paper/FUFVITBL"},"agent_actions":{"view_html":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO","download_json":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO.json","view_paper":"https://pith.science/paper/FUFVITBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06781&json=true","fetch_graph":"https://pith.science/api/pith-number/FUFVITBLV4CSLA6TU43N4AEJRO/graph.json","fetch_events":"https://pith.science/api/pith-number/FUFVITBLV4CSLA6TU43N4AEJRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO/action/storage_attestation","attest_author":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO/action/author_attestation","sign_citation":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO/action/citation_signature","submit_replication":"https://pith.science/pith/FUFVITBLV4CSLA6TU43N4AEJRO/action/replication_record"}},"created_at":"2026-07-05T10:27:42.170291+00:00","updated_at":"2026-07-05T10:27:42.170291+00:00"}