{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PHVMBWDTTJNDVLSJDK54W5YKJ","short_pith_number":"pith:3PHVMBWD","schema_version":"1.0","canonical_sha256":"dbcf5606c39cd2d1d57248d5de5bb8524255666e285ee67f16f5e3dfc4443243","source":{"kind":"arxiv","id":"2412.01708","version":1},"attestation_state":"computed","paper":{"title":"Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaao Chen, Jing Shao, Jingyi Chai, Rui Ye, Siheng Chen, Xianghe Pang, Xiaowen Dong, Zhenfei Yin, Zhen Xiang","submitted_at":"2024-12-02T16:55:03Z","abstract_excerpt":"Scholarly peer review is a cornerstone of scientific advancement, but the system is under strain due to increasing manuscript submissions and the labor-intensive nature of the process. Recent advancements in large language models (LLMs) have led to their integration into peer review, with promising results such as substantial overlaps between LLM- and human-generated reviews. However, the unchecked adoption of LLMs poses significant risks to the integrity of the peer review system. In this study, we comprehensively analyze the vulnerabilities of LLM-generated reviews by focusing on manipulatio"},"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":"2412.01708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T16:55:03Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"602f88780055beb48cabaad134f7ddb0afd79e8348f11fccc1432984f32fc699","abstract_canon_sha256":"93dcb48c9d250f8fc4b92095e9e4d661b872270cf310ce6a152200fb5aa97a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:17.766685Z","signature_b64":"m5UnxRHv58dalSR7dTQ9Lx4ySy5Y6QF5dy0xIDnP+a4q8ghF9OeJcEqAyqpczIcdC2hVW9PDQNPP5CnRwkibBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbcf5606c39cd2d1d57248d5de5bb8524255666e285ee67f16f5e3dfc4443243","last_reissued_at":"2026-07-05T09:43:17.766169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:17.766169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaao Chen, Jing Shao, Jingyi Chai, Rui Ye, Siheng Chen, Xianghe Pang, Xiaowen Dong, Zhenfei Yin, Zhen Xiang","submitted_at":"2024-12-02T16:55:03Z","abstract_excerpt":"Scholarly peer review is a cornerstone of scientific advancement, but the system is under strain due to increasing manuscript submissions and the labor-intensive nature of the process. Recent advancements in large language models (LLMs) have led to their integration into peer review, with promising results such as substantial overlaps between LLM- and human-generated reviews. However, the unchecked adoption of LLMs poses significant risks to the integrity of the peer review system. In this study, we comprehensively analyze the vulnerabilities of LLM-generated reviews by focusing on manipulatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01708","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/2412.01708/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":"2412.01708","created_at":"2026-07-05T09:43:17.766232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01708v1","created_at":"2026-07-05T09:43:17.766232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01708","created_at":"2026-07-05T09:43:17.766232+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PHVMBWDTTJN","created_at":"2026-07-05T09:43:17.766232+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PHVMBWDTTJNDVLS","created_at":"2026-07-05T09:43:17.766232+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PHVMBWD","created_at":"2026-07-05T09:43:17.766232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25057","citing_title":"LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23233","citing_title":"Judgment-Grounded Expansion for Peer Review Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20897","citing_title":"PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13044","citing_title":"No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13349","citing_title":"From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05206","citing_title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18801","citing_title":"Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":242,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11810","citing_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","ref_index":210,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13400","citing_title":"Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26506","citing_title":"SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ","json":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ.json","graph_json":"https://pith.science/api/pith-number/3PHVMBWDTTJNDVLSJDK54W5YKJ/graph.json","events_json":"https://pith.science/api/pith-number/3PHVMBWDTTJNDVLSJDK54W5YKJ/events.json","paper":"https://pith.science/paper/3PHVMBWD"},"agent_actions":{"view_html":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ","download_json":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ.json","view_paper":"https://pith.science/paper/3PHVMBWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01708&json=true","fetch_graph":"https://pith.science/api/pith-number/3PHVMBWDTTJNDVLSJDK54W5YKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3PHVMBWDTTJNDVLSJDK54W5YKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ/action/storage_attestation","attest_author":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ/action/author_attestation","sign_citation":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ/action/citation_signature","submit_replication":"https://pith.science/pith/3PHVMBWDTTJNDVLSJDK54W5YKJ/action/replication_record"}},"created_at":"2026-07-05T09:43:17.766232+00:00","updated_at":"2026-07-05T09:43:17.766232+00:00"}