{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2ABJ7ZHAW2FRHMJZWSIYFZVBF","short_pith_number":"pith:K2ABJ7ZH","schema_version":"1.0","canonical_sha256":"568014ff2705b4589d89cda48c173509636eebc12bc1fc09588b743876ee27fe","source":{"kind":"arxiv","id":"2508.18642","version":2},"attestation_state":"computed","paper":{"title":"RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bosi Wen, Haorui Wang, Jianxing Liao, Rui Yang, Runzhi Shi, Tian Zhang, Xiao Feng, Yusong Zhang, Ziying Wang","submitted_at":"2025-08-26T03:40:06Z","abstract_excerpt":"Large language models are extensively utilized in creative writing applications. Creative writing requires a balance between subjective writing quality (e.g., literariness and emotional expression) and objective constraint following (e.g., format requirements and word limits). Existing methods find it difficult to balance these two aspects: single reward strategies fail to improve both abilities simultaneously, while fixed-weight mixed-reward methods lack the ability to adapt to different writing scenarios. To address this problem, we propose Reinforcement Learning with Mixed Rewards (RLMR), u"},"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":"2508.18642","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T03:40:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"38736d7542838d19d652c04d0d026300eefac784a4b28c6350bd02c7b25a7cf7","abstract_canon_sha256":"a187b09625a6b67c5aceaea187b55cc946675c5eb2dbc0ce4840c606f7fdc436"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:52.142534Z","signature_b64":"UkoTOhOqpMM4BzHuCguiybStYHyxvVrNBt16LBSUFOwMggoj87rDpuDWUNgs98EFdywK/4FoC0w1R2iHxtVGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568014ff2705b4589d89cda48c173509636eebc12bc1fc09588b743876ee27fe","last_reissued_at":"2026-07-05T12:00:52.142069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:52.142069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bosi Wen, Haorui Wang, Jianxing Liao, Rui Yang, Runzhi Shi, Tian Zhang, Xiao Feng, Yusong Zhang, Ziying Wang","submitted_at":"2025-08-26T03:40:06Z","abstract_excerpt":"Large language models are extensively utilized in creative writing applications. Creative writing requires a balance between subjective writing quality (e.g., literariness and emotional expression) and objective constraint following (e.g., format requirements and word limits). Existing methods find it difficult to balance these two aspects: single reward strategies fail to improve both abilities simultaneously, while fixed-weight mixed-reward methods lack the ability to adapt to different writing scenarios. To address this problem, we propose Reinforcement Learning with Mixed Rewards (RLMR), u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18642","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/2508.18642/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":"2508.18642","created_at":"2026-07-05T12:00:52.142125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18642v2","created_at":"2026-07-05T12:00:52.142125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18642","created_at":"2026-07-05T12:00:52.142125+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2ABJ7ZHAW2F","created_at":"2026-07-05T12:00:52.142125+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2ABJ7ZHAW2FRHMJ","created_at":"2026-07-05T12:00:52.142125+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2ABJ7ZH","created_at":"2026-07-05T12:00:52.142125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":185,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF","json":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF.json","graph_json":"https://pith.science/api/pith-number/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/graph.json","events_json":"https://pith.science/api/pith-number/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/events.json","paper":"https://pith.science/paper/K2ABJ7ZH"},"agent_actions":{"view_html":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF","download_json":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF.json","view_paper":"https://pith.science/paper/K2ABJ7ZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18642&json=true","fetch_graph":"https://pith.science/api/pith-number/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/graph.json","fetch_events":"https://pith.science/api/pith-number/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/action/storage_attestation","attest_author":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/action/author_attestation","sign_citation":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/action/citation_signature","submit_replication":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/action/replication_record"}},"created_at":"2026-07-05T12:00:52.142125+00:00","updated_at":"2026-07-05T12:00:52.142125+00:00"}