{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B6MPFISKKADPVICB5RNHWEDOMM","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":"e36f30bde2286e6a8d9e777cb3ef365e29f1a3cac14562be74972ce238dc0644","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:21:43Z","title_canon_sha256":"00dd55c1762b1fa60a256539e0a2a135390a7d95636059954659284ac57c5f37"},"schema_version":"1.0","source":{"id":"2410.20774","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20774","created_at":"2026-07-05T10:56:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20774v2","created_at":"2026-07-05T10:56:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20774","created_at":"2026-07-05T10:56:35Z"},{"alias_kind":"pith_short_12","alias_value":"B6MPFISKKADP","created_at":"2026-07-05T10:56:35Z"},{"alias_kind":"pith_short_16","alias_value":"B6MPFISKKADPVICB","created_at":"2026-07-05T10:56:35Z"},{"alias_kind":"pith_short_8","alias_value":"B6MPFISK","created_at":"2026-07-05T10:56:35Z"}],"graph_snapshots":[{"event_id":"sha256:09e5438c03fe09eff2cc21e142f9d64076f58d58229b86075d5fb5f9039f3fa9","target":"graph","created_at":"2026-07-05T10:56:35Z","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/2410.20774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In line with the principle of honesty, there has been a growing effort to train large language models (LLMs) to generate outputs containing epistemic markers. However, evaluation in the presence of epistemic markers has been largely overlooked, raising a critical question: Could the use of epistemic markers in LLM-generated outputs lead to unintended negative consequences? To address this, we present EMBER, a benchmark designed to assess the robustness of LLM-judges to epistemic markers in both single and pairwise evaluation settings. Our findings, based on evaluations using EMBER, reveal that","authors_text":"Dongryeol Lee, Joonsuk Park, Kyomin Jung, Yerin Hwang, Yongil Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:21:43Z","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20774","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":"sha256:62ab279814b01dfc67cb113384b4d3ac76c83e4916ba917f3160ed3702c3db88","target":"record","created_at":"2026-07-05T10:56:35Z","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":"e36f30bde2286e6a8d9e777cb3ef365e29f1a3cac14562be74972ce238dc0644","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:21:43Z","title_canon_sha256":"00dd55c1762b1fa60a256539e0a2a135390a7d95636059954659284ac57c5f37"},"schema_version":"1.0","source":{"id":"2410.20774","kind":"arxiv","version":2}},"canonical_sha256":"0f98f2a24a5006faa041ec5a7b106e631968894ad51b032a71d8574952a3bd5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f98f2a24a5006faa041ec5a7b106e631968894ad51b032a71d8574952a3bd5b","first_computed_at":"2026-07-05T10:56:35.107026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:35.107026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ytm0d+vCAAMiLG/WjBnrrSbRCdnQKzLa16LpwNg149a4axZTzUILnEaoLbs34fjv70T2YCMVr6sWtj6kceHyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:35.107591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20774","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62ab279814b01dfc67cb113384b4d3ac76c83e4916ba917f3160ed3702c3db88","sha256:09e5438c03fe09eff2cc21e142f9d64076f58d58229b86075d5fb5f9039f3fa9"],"state_sha256":"acc522284dcfaa22163cb9601c58e449f5639f29da305baff16a9ac8decf80d1"}