{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W4CYIMYOT4TTW5QCEHACOZNT4Y","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":"f49a1b1e0d8618e87d77e0c4b1a4943f7df30d45a5c366fb74201e4642fd0c02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T13:05:13Z","title_canon_sha256":"a359e863799c7a4f09eb42eba7e1a0656c0d189b0a986f603b84e81d0efaee33"},"schema_version":"1.0","source":{"id":"2601.07506","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.07506","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2601.07506v2","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07506","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"W4CYIMYOT4TT","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"W4CYIMYOT4TTW5QC","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"W4CYIMYO","created_at":"2026-06-11T01:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:2f0a042b7459c48d6594f279549fa20b868671e9a7352e7c896f9bbe243c7094","target":"graph","created_at":"2026-06-11T01:09:26Z","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/2601.07506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about their ability to adhere to a provided reference. We identify a critical failure mode of such reference-based LLM QA evaluation: when the provided reference conflicts with the judge model's parametric knowledge, the resulting scores become unreliable, substantially degrading evaluation fidelity. To study this phenomenon systematically, we introduce a controlled swapped-reference QA framework that induces reference-belief","authors_text":"Dongryeol Lee, Kyomin Jung, Minwoo Lee, Taegwan Kang, Yerin Hwang, Younhyung Chae","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T13:05:13Z","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07506","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:c6e7d653aa815c4e4c1d816492bf876586511a70b0396e254d000fa42779efd2","target":"record","created_at":"2026-06-11T01:09:26Z","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":"f49a1b1e0d8618e87d77e0c4b1a4943f7df30d45a5c366fb74201e4642fd0c02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T13:05:13Z","title_canon_sha256":"a359e863799c7a4f09eb42eba7e1a0656c0d189b0a986f603b84e81d0efaee33"},"schema_version":"1.0","source":{"id":"2601.07506","kind":"arxiv","version":2}},"canonical_sha256":"b70584330e9f273b760221c02765b3e62da3c29c658d77d7005fd1e4a7f74c09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b70584330e9f273b760221c02765b3e62da3c29c658d77d7005fd1e4a7f74c09","first_computed_at":"2026-06-11T01:09:26.541120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:26.541120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JrKjYoWuVZR2Y1sko1d7LCaFouQaXtUJRyYiSA1tne01VZvhzZBh2f19Ef5Fcj1BxW5NGaX42YDpWgNOKWo0BA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:26.542133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.07506","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6e7d653aa815c4e4c1d816492bf876586511a70b0396e254d000fa42779efd2","sha256:2f0a042b7459c48d6594f279549fa20b868671e9a7352e7c896f9bbe243c7094"],"state_sha256":"5117f613a8de124a0f347dc80e2a126347a592bfba86944079560ce9fba5f041"}