{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P55SUY5YHEJJN5RBBAL3FBCZJI","short_pith_number":"pith:P55SUY5Y","schema_version":"1.0","canonical_sha256":"7f7b2a63b8391296f6210817b284594a03e1edc07759c4d288eb387ae95c4a6f","source":{"kind":"arxiv","id":"2508.21476","version":1},"attestation_state":"computed","paper":{"title":"Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Lu, Dawei Yin, Dongdong Shen, Long Xia, Xiaolong Wei, Xingyu Zhang, Zhejun Zhao","submitted_at":"2025-08-29T10:00:55Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language Models (SLMs) offers a promising alternative, but current methods like Supervised Fine-Tuning (SFT) struggle with novelty, and Reinforcement Learning from Human Feedback (RLHF) is costly. This paper explores two distinct AI-driven reward strategies within a Reinforcement Learning from AI Feedback (RLAIF) framework to ignite the creative writing of a 7B-parameter SLM, specifically for generating Chinese greetings. Th"},"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":"2508.21476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T10:00:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0f053a8ee2a707559ebc469321fc9099eae5ced5a7f6bc70aa3aa68520eb631","abstract_canon_sha256":"e059e367aaca030c0896247567f78a87a3ea1063514b677bb55cccc23b9d6191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:35.459962Z","signature_b64":"ue2zLG8R7WOTEwr27mJqUrt7GEu8LtUA4wuFouD6f65os3xGyRtI8JSIefnGBJ9Jyb9wDLjl9Gm8b+IBlXj/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f7b2a63b8391296f6210817b284594a03e1edc07759c4d288eb387ae95c4a6f","last_reissued_at":"2026-07-05T12:01:35.459494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:35.459494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Lu, Dawei Yin, Dongdong Shen, Long Xia, Xiaolong Wei, Xingyu Zhang, Zhejun Zhao","submitted_at":"2025-08-29T10:00:55Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language Models (SLMs) offers a promising alternative, but current methods like Supervised Fine-Tuning (SFT) struggle with novelty, and Reinforcement Learning from Human Feedback (RLHF) is costly. This paper explores two distinct AI-driven reward strategies within a Reinforcement Learning from AI Feedback (RLAIF) framework to ignite the creative writing of a 7B-parameter SLM, specifically for generating Chinese greetings. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21476","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/2508.21476/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":"2508.21476","created_at":"2026-07-05T12:01:35.459543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21476v1","created_at":"2026-07-05T12:01:35.459543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21476","created_at":"2026-07-05T12:01:35.459543+00:00"},{"alias_kind":"pith_short_12","alias_value":"P55SUY5YHEJJ","created_at":"2026-07-05T12:01:35.459543+00:00"},{"alias_kind":"pith_short_16","alias_value":"P55SUY5YHEJJN5RB","created_at":"2026-07-05T12:01:35.459543+00:00"},{"alias_kind":"pith_short_8","alias_value":"P55SUY5Y","created_at":"2026-07-05T12:01:35.459543+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/P55SUY5YHEJJN5RBBAL3FBCZJI","json":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI.json","graph_json":"https://pith.science/api/pith-number/P55SUY5YHEJJN5RBBAL3FBCZJI/graph.json","events_json":"https://pith.science/api/pith-number/P55SUY5YHEJJN5RBBAL3FBCZJI/events.json","paper":"https://pith.science/paper/P55SUY5Y"},"agent_actions":{"view_html":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI","download_json":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI.json","view_paper":"https://pith.science/paper/P55SUY5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21476&json=true","fetch_graph":"https://pith.science/api/pith-number/P55SUY5YHEJJN5RBBAL3FBCZJI/graph.json","fetch_events":"https://pith.science/api/pith-number/P55SUY5YHEJJN5RBBAL3FBCZJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI/action/storage_attestation","attest_author":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI/action/author_attestation","sign_citation":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI/action/citation_signature","submit_replication":"https://pith.science/pith/P55SUY5YHEJJN5RBBAL3FBCZJI/action/replication_record"}},"created_at":"2026-07-05T12:01:35.459543+00:00","updated_at":"2026-07-05T12:01:35.459543+00:00"}