{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ZKADCHWTIL4LPCSIDJPVADNVK","short_pith_number":"pith:2ZKADCHW","schema_version":"1.0","canonical_sha256":"d6540188f69a17c5bc5240d2fa806daab85878d040b1142b557a1b3f01566a84","source":{"kind":"arxiv","id":"2503.15620","version":1},"attestation_state":"computed","paper":{"title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Austin Xu, Semih Yavuz, Shafiq Joty, Srijan Bansal, Yifei Ming","submitted_at":"2025-03-19T18:09:19Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.15620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T18:09:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3192d11f1aaa33fd16d83c9cda24f4592778b79b4c6f495618e0e88e3ca4f4a2","abstract_canon_sha256":"6ae9a601b1207168d40b55d321a4b23234424f8cede7b75bcd6124f266646582"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:54.403551Z","signature_b64":"xLr7eRDPKbPSwwNxoxK8vU5UQNxir4Pq12XtqERIp1AjEOWWnq/ZxBDrJukGPPWUUEF1yxTfZWD4UMVwrnDADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6540188f69a17c5bc5240d2fa806daab85878d040b1142b557a1b3f01566a84","last_reissued_at":"2026-07-05T10:35:54.402917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:54.402917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Austin Xu, Semih Yavuz, Shafiq Joty, Srijan Bansal, Yifei Ming","submitted_at":"2025-03-19T18:09:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15620","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.15620/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.15620","created_at":"2026-07-05T10:35:54.402986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15620v1","created_at":"2026-07-05T10:35:54.402986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15620","created_at":"2026-07-05T10:35:54.402986+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZKADCHWTIL4","created_at":"2026-07-05T10:35:54.402986+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZKADCHWTIL4LPCS","created_at":"2026-07-05T10:35:54.402986+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZKADCHW","created_at":"2026-07-05T10:35:54.402986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23542","citing_title":"On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK","json":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK.json","graph_json":"https://pith.science/api/pith-number/2ZKADCHWTIL4LPCSIDJPVADNVK/graph.json","events_json":"https://pith.science/api/pith-number/2ZKADCHWTIL4LPCSIDJPVADNVK/events.json","paper":"https://pith.science/paper/2ZKADCHW"},"agent_actions":{"view_html":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK","download_json":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK.json","view_paper":"https://pith.science/paper/2ZKADCHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15620&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZKADCHWTIL4LPCSIDJPVADNVK/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZKADCHWTIL4LPCSIDJPVADNVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK/action/storage_attestation","attest_author":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK/action/author_attestation","sign_citation":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK/action/citation_signature","submit_replication":"https://pith.science/pith/2ZKADCHWTIL4LPCSIDJPVADNVK/action/replication_record"}},"created_at":"2026-07-05T10:35:54.402986+00:00","updated_at":"2026-07-05T10:35:54.402986+00:00"}