{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HY63NN5ZNYZB5RSDIORDN6TEWN","short_pith_number":"pith:HY63NN5Z","schema_version":"1.0","canonical_sha256":"3e3db6b7b96e321ec64343a236fa64b36d1a4ac9709fba0aa3e1c0b0fe098353","source":{"kind":"arxiv","id":"2606.19544","version":1},"attestation_state":"computed","paper":{"title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"D. Alex Hughes, Justin D. Norman, Michael U. Rivera","submitted_at":"2026-06-17T19:37:13Z","abstract_excerpt":"LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 20"},"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":"2606.19544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T19:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"7bafefce25b7c1d532538177eeefe8686e2f4faac974982217d6e1ddb48e7d03","abstract_canon_sha256":"542aee541ed2f2ee7beef78a67cb92dc20ec8a804d0fa65dcdf83f9dc78935d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:28.585762Z","signature_b64":"wAtxVnwkX74g2SzCHSlc5vuThEmBAn4S0QY3JNq9RFdz1+0NuZtvpUMfAJPOMuF/mIvAaodEp9cf/PLEnIBxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e3db6b7b96e321ec64343a236fa64b36d1a4ac9709fba0aa3e1c0b0fe098353","last_reissued_at":"2026-06-19T16:12:28.585399Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:28.585399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"D. Alex Hughes, Justin D. Norman, Michael U. Rivera","submitted_at":"2026-06-17T19:37:13Z","abstract_excerpt":"LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 20"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19544","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/2606.19544/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":"2606.19544","created_at":"2026-06-19T16:12:28.585462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19544v1","created_at":"2026-06-19T16:12:28.585462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19544","created_at":"2026-06-19T16:12:28.585462+00:00"},{"alias_kind":"pith_short_12","alias_value":"HY63NN5ZNYZB","created_at":"2026-06-19T16:12:28.585462+00:00"},{"alias_kind":"pith_short_16","alias_value":"HY63NN5ZNYZB5RSD","created_at":"2026-06-19T16:12:28.585462+00:00"},{"alias_kind":"pith_short_8","alias_value":"HY63NN5Z","created_at":"2026-06-19T16:12:28.585462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN","json":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN.json","graph_json":"https://pith.science/api/pith-number/HY63NN5ZNYZB5RSDIORDN6TEWN/graph.json","events_json":"https://pith.science/api/pith-number/HY63NN5ZNYZB5RSDIORDN6TEWN/events.json","paper":"https://pith.science/paper/HY63NN5Z"},"agent_actions":{"view_html":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN","download_json":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN.json","view_paper":"https://pith.science/paper/HY63NN5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19544&json=true","fetch_graph":"https://pith.science/api/pith-number/HY63NN5ZNYZB5RSDIORDN6TEWN/graph.json","fetch_events":"https://pith.science/api/pith-number/HY63NN5ZNYZB5RSDIORDN6TEWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/action/storage_attestation","attest_author":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/action/author_attestation","sign_citation":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/action/citation_signature","submit_replication":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/action/replication_record"}},"created_at":"2026-06-19T16:12:28.585462+00:00","updated_at":"2026-06-19T16:12:28.585462+00:00"}