{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AOYKVHR7IQLU22PEZF6RI7FCS6","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":"5fdf9bce29d9209030aa88f4622fcad68c46f84e292fbd45749adc8ad1af810e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-14T07:14:27Z","title_canon_sha256":"1d831b801f8cec55e4e62900f0be7ecb90d414a6071ee7c5c598832814f3f15f"},"schema_version":"1.0","source":{"id":"2504.09946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09946","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09946v2","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09946","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"AOYKVHR7IQLU","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_16","alias_value":"AOYKVHR7IQLU22PE","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_8","alias_value":"AOYKVHR7","created_at":"2026-07-05T10:50:48Z"}],"graph_snapshots":[{"event_id":"sha256:ee26d411d2f29d00012334ac0ed83dc162c5576e560c9c87f739e11eda35e19f","target":"graph","created_at":"2026-07-05T10:50:48Z","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/2504.09946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge settings. We present a comprehensive benchmark comparing judging biases between LLMs and LRMs across both subjective preference-alignment datasets and objective fact-based datasets. Through investigation of bandwagon, authority, position, and distraction biases, we uncover four key findings: (1) despite their advanced reasoning capabilities, LRMs remain susceptible to the above biases; (2) LRMs demonstrate better robu","authors_text":"Bingsheng He, Dawn Song, Nuo Chen, Qian Wang, Wenxuan Zhang, Xuandong Zhao, Zhanzhi Lou, Zhenheng Tang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-14T07:14:27Z","title":"Assessing Judging Bias in Large Reasoning Models: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09946","kind":"arxiv","version":2},"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:c01b8e924dc2a3d6cf3d12a576c384d4fce39c6550b9779169c5715defd3bdcb","target":"record","created_at":"2026-07-05T10:50:48Z","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":"5fdf9bce29d9209030aa88f4622fcad68c46f84e292fbd45749adc8ad1af810e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-14T07:14:27Z","title_canon_sha256":"1d831b801f8cec55e4e62900f0be7ecb90d414a6071ee7c5c598832814f3f15f"},"schema_version":"1.0","source":{"id":"2504.09946","kind":"arxiv","version":2}},"canonical_sha256":"03b0aa9e3f44174d69e4c97d147ca2979bd08475b1149ab8630cfc29aa6feee3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03b0aa9e3f44174d69e4c97d147ca2979bd08475b1149ab8630cfc29aa6feee3","first_computed_at":"2026-07-05T10:50:48.851536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:48.851536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NJvfuWuC00dQTGaERG9fhc0rWLHfFQaY/yBUAUWUVxaPMCNECSzk+yk1WFIuytu6a5DRTxE9vp8giYT9MV3GDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:48.852035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c01b8e924dc2a3d6cf3d12a576c384d4fce39c6550b9779169c5715defd3bdcb","sha256:ee26d411d2f29d00012334ac0ed83dc162c5576e560c9c87f739e11eda35e19f"],"state_sha256":"b76a0e291432360063a4594e13a1eff2592d4f5871ac1afbd8e363c8f66729d8"}