{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:33RFBHL5SIUZUGUSO7OGYNUXOH","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":"f7854726a5c2f22c530cf5db7a069a5019790cfb5aba80aede1a225515156bf3","cross_cats_sorted":["cs.CY","cs.ET"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T04:32:13Z","title_canon_sha256":"93942054cbb4babd05391027c8f902c10ffb9bef222c6d3692c93661459acd08"},"schema_version":"1.0","source":{"id":"2605.25415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25415","created_at":"2026-05-26T02:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25415v1","created_at":"2026-05-26T02:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25415","created_at":"2026-05-26T02:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"33RFBHL5SIUZ","created_at":"2026-05-26T02:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"33RFBHL5SIUZUGUS","created_at":"2026-05-26T02:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"33RFBHL5","created_at":"2026-05-26T02:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:f434c7035c8a7be793194ce9976094b73c7d169addf1fc4eb3f1c284b44ec566","target":"graph","created_at":"2026-05-26T02:04:33Z","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/2605.25415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood. We present a systematic benchmark of LLM-as-a-Reviewer on 898 papers stratified from NeurIPS and ICLR, evaluating 12 LLMs along three axes: rating calibration, divergence from human reviewers, and resistance to prompt injection embedded via an invisible font-mapping attack. We find that LLMs systematically overrate weaker submissions and diverge from humans in topical emphasis, under-flagging Clarity an","authors_text":"Changjia Zhu, Chen Chen, Junjie Xiong, Junyu Wang, Lingyao Li, Renkai Ma, Runlong Yu, Zhicong Lu","cross_cats":["cs.CY","cs.ET"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T04:32:13Z","title":"LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25415","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":"sha256:7e6ada7f9078211fa8a83964e637d483bd768a8de61a05b269276bbb8762dbfc","target":"record","created_at":"2026-05-26T02:04:33Z","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":"f7854726a5c2f22c530cf5db7a069a5019790cfb5aba80aede1a225515156bf3","cross_cats_sorted":["cs.CY","cs.ET"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T04:32:13Z","title_canon_sha256":"93942054cbb4babd05391027c8f902c10ffb9bef222c6d3692c93661459acd08"},"schema_version":"1.0","source":{"id":"2605.25415","kind":"arxiv","version":1}},"canonical_sha256":"dee2509d7d92299a1a9277dc6c369771da18c9a64545250c13dfee3e205441c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dee2509d7d92299a1a9277dc6c369771da18c9a64545250c13dfee3e205441c3","first_computed_at":"2026-05-26T02:04:33.814281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:33.814281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lLP9cLlEBZ/8D3/qAFEN5BtRxh6IIzhWrrTbi1FLKsQ5PEO7J0j0Kns2XcA6KNSnktu++IH76JEhw4C5/HL2Dg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:33.815091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6ada7f9078211fa8a83964e637d483bd768a8de61a05b269276bbb8762dbfc","sha256:f434c7035c8a7be793194ce9976094b73c7d169addf1fc4eb3f1c284b44ec566"],"state_sha256":"a92b1ea35f14becfcd6a455266ba305c1767441b353f8bc5ae3237592b427687"}