{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K2ABJ7ZHAW2FRHMJZWSIYFZVBF","short_pith_number":"pith:K2ABJ7ZH","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"},"canonical_sha256":"568014ff2705b4589d89cda48c173509636eebc12bc1fc09588b743876ee27fe","source":{"kind":"arxiv","id":"2508.18642","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18642","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18642v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18642","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"K2ABJ7ZHAW2F","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"K2ABJ7ZHAW2FRHMJ","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"K2ABJ7ZH","created_at":"2026-07-05T12:00:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K2ABJ7ZHAW2FRHMJZWSIYFZVBF","target":"record","payload":{"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"},"canonical_sha256":"568014ff2705b4589d89cda48c173509636eebc12bc1fc09588b743876ee27fe","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"},"source_kind":"arxiv","source_id":"2508.18642","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S4TujcFbyM9xdMmb5NeVPrwi2eWfF7Aq9SKc5SThIDiOpBF3B0pzaHoTGtFi4iQ4OaLPcdKQ4Y1CYnDgfIljAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:59:35.710213Z"},"content_sha256":"c1df6eae55d42821049063f947f7773f3f5af863fccdcd3fb81978bedc83154d","schema_version":"1.0","event_id":"sha256:c1df6eae55d42821049063f947f7773f3f5af863fccdcd3fb81978bedc83154d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K2ABJ7ZHAW2FRHMJZWSIYFZVBF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuQuz2cs3F/8q8+Q8ph2CUljiW3ARNsmDfOT8l1hBRiw1DXmlDHtmPd/S2LPWycmfDroelCdKJaFIl31QgmpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:59:35.710714Z"},"content_sha256":"c6657a23b9fc88af5dd7c479524df08bdb4b00d668db184f24530b1a97915828","schema_version":"1.0","event_id":"sha256:c6657a23b9fc88af5dd7c479524df08bdb4b00d668db184f24530b1a97915828"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/bundle.json","state_url":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T08:59:35Z","links":{"resolver":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF","bundle":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/bundle.json","state":"https://pith.science/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2ABJ7ZHAW2FRHMJZWSIYFZVBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2ABJ7ZHAW2FRHMJZWSIYFZVBF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a187b09625a6b67c5aceaea187b55cc946675c5eb2dbc0ce4840c606f7fdc436","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T03:40:06Z","title_canon_sha256":"38736d7542838d19d652c04d0d026300eefac784a4b28c6350bd02c7b25a7cf7"},"schema_version":"1.0","source":{"id":"2508.18642","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18642","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18642v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18642","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"K2ABJ7ZHAW2F","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"K2ABJ7ZHAW2FRHMJ","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"K2ABJ7ZH","created_at":"2026-07-05T12:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:c6657a23b9fc88af5dd7c479524df08bdb4b00d668db184f24530b1a97915828","target":"graph","created_at":"2026-07-05T12:00:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.18642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bosi Wen, Haorui Wang, Jianxing Liao, Rui Yang, Runzhi Shi, Tian Zhang, Xiao Feng, Yusong Zhang, Ziying Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T03:40:06Z","title":"RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18642","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1df6eae55d42821049063f947f7773f3f5af863fccdcd3fb81978bedc83154d","target":"record","created_at":"2026-07-05T12:00:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a187b09625a6b67c5aceaea187b55cc946675c5eb2dbc0ce4840c606f7fdc436","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T03:40:06Z","title_canon_sha256":"38736d7542838d19d652c04d0d026300eefac784a4b28c6350bd02c7b25a7cf7"},"schema_version":"1.0","source":{"id":"2508.18642","kind":"arxiv","version":2}},"canonical_sha256":"568014ff2705b4589d89cda48c173509636eebc12bc1fc09588b743876ee27fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568014ff2705b4589d89cda48c173509636eebc12bc1fc09588b743876ee27fe","first_computed_at":"2026-07-05T12:00:52.142069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:52.142069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkoTOhOqpMM4BzHuCguiybStYHyxvVrNBt16LBSUFOwMggoj87rDpuDWUNgs98EFdywK/4FoC0w1R2iHxtVGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:52.142534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18642","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1df6eae55d42821049063f947f7773f3f5af863fccdcd3fb81978bedc83154d","sha256:c6657a23b9fc88af5dd7c479524df08bdb4b00d668db184f24530b1a97915828"],"state_sha256":"c2309fa6209ff4dfe4d4708f4e45e20d325af1b798d806fde8dbbda50070284a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7+2l7JvAyoaw29k88KxW9TPa9yttrCw1CSYsa4WIL+vKHtGNXrUGP8BllR2y8eL/mq6D6/1w6+EbEBl9N4qBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:59:35.714092Z","bundle_sha256":"f49d9af66b78a9ca30758abbcec66c6f53544a880bc5b5997f9e53167bec885c"}}