{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P55SUY5YHEJJN5RBBAL3FBCZJI","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":"e059e367aaca030c0896247567f78a87a3ea1063514b677bb55cccc23b9d6191","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T10:00:55Z","title_canon_sha256":"d0f053a8ee2a707559ebc469321fc9099eae5ced5a7f6bc70aa3aa68520eb631"},"schema_version":"1.0","source":{"id":"2508.21476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21476","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21476v1","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21476","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"P55SUY5YHEJJ","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"P55SUY5YHEJJN5RB","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"P55SUY5Y","created_at":"2026-07-05T12:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:4cd29df530d86069287613f2a0677049bd42fea522605d598b30c6b468db9075","target":"graph","created_at":"2026-07-05T12:01:35Z","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/2508.21476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Lu, Dawei Yin, Dongdong Shen, Long Xia, Xiaolong Wei, Xingyu Zhang, Zhejun Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T10:00:55Z","title":"Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21476","kind":"arxiv","version":1},"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":"sha256:77928ea7f8c458309f3643dccd5ba8f1c0ea332ff48ec9bd4a7badb8f3c306b2","target":"record","created_at":"2026-07-05T12:01:35Z","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":"e059e367aaca030c0896247567f78a87a3ea1063514b677bb55cccc23b9d6191","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T10:00:55Z","title_canon_sha256":"d0f053a8ee2a707559ebc469321fc9099eae5ced5a7f6bc70aa3aa68520eb631"},"schema_version":"1.0","source":{"id":"2508.21476","kind":"arxiv","version":1}},"canonical_sha256":"7f7b2a63b8391296f6210817b284594a03e1edc07759c4d288eb387ae95c4a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f7b2a63b8391296f6210817b284594a03e1edc07759c4d288eb387ae95c4a6f","first_computed_at":"2026-07-05T12:01:35.459494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:35.459494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ue2zLG8R7WOTEwr27mJqUrt7GEu8LtUA4wuFouD6f65os3xGyRtI8JSIefnGBJ9Jyb9wDLjl9Gm8b+IBlXj/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:35.459962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77928ea7f8c458309f3643dccd5ba8f1c0ea332ff48ec9bd4a7badb8f3c306b2","sha256:4cd29df530d86069287613f2a0677049bd42fea522605d598b30c6b468db9075"],"state_sha256":"0f2d81057fa51ea4de2e3eece983d2311bfd0c4879336875aa0355561cbe356d"}