{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RACFST22NR2UFVDZZOOTJAY3IV","short_pith_number":"pith:RACFST22","schema_version":"1.0","canonical_sha256":"8804594f5a6c7542d479cb9d34831b45774d5373e84416e380f156a4e707c7be","source":{"kind":"arxiv","id":"2608.01666","version":1},"attestation_state":"computed","paper":{"title":"Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fan Zhang, Fengxian Ji, Jingpu Yang, Juanfan Wu, Min Peng, Qianqian Xie, Xiuying Chen, Yuke Li, Yu Xie, Zhexuan Cui, Zhuohan Xie","submitted_at":"2026-08-03T04:01:02Z","abstract_excerpt":"However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question. To address this question, we propose SciStyleBench, a unified three-component benchmark for diagnosing and mitigating stylistic bias in LLM-based idea evaluation: (i) First, SciStyleStage, a three-stage evaluation environment that applies controlled stylistic perturbations to fixed scientific content across three settings no context, fixed-domain context, and open-domain retrieval context, covering 600 scientific ideas and 15 style var"},"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":"2608.01666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T04:01:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5417660f7344ab404b653ac4555cc00e726b8dfb5e17c88e67f33bb28ad61a2","abstract_canon_sha256":"8e38f44ba3ea7b5fae2771c1840f1fa6d48c49443bad343ebe4649c727b24ad8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:22.664217Z","signature_b64":"CS4Tr6mzMrbo/Nbef77sGXTy6p/TE/+yFjh2TanOTJEXa/t+K0HB/n3tIZIXZ/ZVDaaYkPPx1ubqlXXqiU7zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8804594f5a6c7542d479cb9d34831b45774d5373e84416e380f156a4e707c7be","last_reissued_at":"2026-08-04T02:06:22.662353Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:22.662353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fan Zhang, Fengxian Ji, Jingpu Yang, Juanfan Wu, Min Peng, Qianqian Xie, Xiuying Chen, Yuke Li, Yu Xie, Zhexuan Cui, Zhuohan Xie","submitted_at":"2026-08-03T04:01:02Z","abstract_excerpt":"However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question. To address this question, we propose SciStyleBench, a unified three-component benchmark for diagnosing and mitigating stylistic bias in LLM-based idea evaluation: (i) First, SciStyleStage, a three-stage evaluation environment that applies controlled stylistic perturbations to fixed scientific content across three settings no context, fixed-domain context, and open-domain retrieval context, covering 600 scientific ideas and 15 style var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01666","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/2608.01666/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":"2608.01666","created_at":"2026-08-04T02:06:22.664122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01666v1","created_at":"2026-08-04T02:06:22.664122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01666","created_at":"2026-08-04T02:06:22.664122+00:00"},{"alias_kind":"pith_short_12","alias_value":"RACFST22NR2U","created_at":"2026-08-04T02:06:22.664122+00:00"},{"alias_kind":"pith_short_16","alias_value":"RACFST22NR2UFVDZ","created_at":"2026-08-04T02:06:22.664122+00:00"},{"alias_kind":"pith_short_8","alias_value":"RACFST22","created_at":"2026-08-04T02:06:22.664122+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/RACFST22NR2UFVDZZOOTJAY3IV","json":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV.json","graph_json":"https://pith.science/api/pith-number/RACFST22NR2UFVDZZOOTJAY3IV/graph.json","events_json":"https://pith.science/api/pith-number/RACFST22NR2UFVDZZOOTJAY3IV/events.json","paper":"https://pith.science/paper/RACFST22"},"agent_actions":{"view_html":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV","download_json":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV.json","view_paper":"https://pith.science/paper/RACFST22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01666&json=true","fetch_graph":"https://pith.science/api/pith-number/RACFST22NR2UFVDZZOOTJAY3IV/graph.json","fetch_events":"https://pith.science/api/pith-number/RACFST22NR2UFVDZZOOTJAY3IV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV/action/storage_attestation","attest_author":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV/action/author_attestation","sign_citation":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV/action/citation_signature","submit_replication":"https://pith.science/pith/RACFST22NR2UFVDZZOOTJAY3IV/action/replication_record"}},"created_at":"2026-08-04T02:06:22.664122+00:00","updated_at":"2026-08-04T02:06:22.664122+00:00"}