{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ZKADCHWTIL4LPCSIDJPVADNVK","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":"6ae9a601b1207168d40b55d321a4b23234424f8cede7b75bcd6124f266646582","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T18:09:19Z","title_canon_sha256":"3192d11f1aaa33fd16d83c9cda24f4592778b79b4c6f495618e0e88e3ca4f4a2"},"schema_version":"1.0","source":{"id":"2503.15620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15620","created_at":"2026-07-05T10:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15620v1","created_at":"2026-07-05T10:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15620","created_at":"2026-07-05T10:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"2ZKADCHWTIL4","created_at":"2026-07-05T10:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"2ZKADCHWTIL4LPCS","created_at":"2026-07-05T10:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"2ZKADCHW","created_at":"2026-07-05T10:35:54Z"}],"graph_snapshots":[{"event_id":"sha256:9e595b570c0527edde5a5a54465aab67dc02d45b45928988fa2661342b2ed7eb","target":"graph","created_at":"2026-07-05T10:35:54Z","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/2503.15620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-deployment monitoring. While judge models -- LLMs finetuned to specialize in assessing and critiquing model outputs -- have been touted as general purpose evaluators, they are typically evaluated only on non-contextual scenarios, such as instruction following. The omission of contextual settings -- those where external information is used as context to generate an output -- is surprising given the increasing prevalen","authors_text":"Austin Xu, Semih Yavuz, Shafiq Joty, Srijan Bansal, Yifei Ming","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T18:09:19Z","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15620","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":"sha256:985fad39aa4f04f8e45d41c511c4b18bad84586dcdd1e0decdc609ffcfe9ce03","target":"record","created_at":"2026-07-05T10:35:54Z","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":"6ae9a601b1207168d40b55d321a4b23234424f8cede7b75bcd6124f266646582","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T18:09:19Z","title_canon_sha256":"3192d11f1aaa33fd16d83c9cda24f4592778b79b4c6f495618e0e88e3ca4f4a2"},"schema_version":"1.0","source":{"id":"2503.15620","kind":"arxiv","version":1}},"canonical_sha256":"d6540188f69a17c5bc5240d2fa806daab85878d040b1142b557a1b3f01566a84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6540188f69a17c5bc5240d2fa806daab85878d040b1142b557a1b3f01566a84","first_computed_at":"2026-07-05T10:35:54.402917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:54.402917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLr7eRDPKbPSwwNxoxK8vU5UQNxir4Pq12XtqERIp1AjEOWWnq/ZxBDrJukGPPWUUEF1yxTfZWD4UMVwrnDADg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:54.403551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:985fad39aa4f04f8e45d41c511c4b18bad84586dcdd1e0decdc609ffcfe9ce03","sha256:9e595b570c0527edde5a5a54465aab67dc02d45b45928988fa2661342b2ed7eb"],"state_sha256":"865bfaa590ceb0f158ea4293b16a2443866b8b135423623dcba129953c85e876"}