{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HY63NN5ZNYZB5RSDIORDN6TEWN","short_pith_number":"pith:HY63NN5Z","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"},"canonical_sha256":"3e3db6b7b96e321ec64343a236fa64b36d1a4ac9709fba0aa3e1c0b0fe098353","source":{"kind":"arxiv","id":"2606.19544","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19544","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19544v1","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19544","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"HY63NN5ZNYZB","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"HY63NN5ZNYZB5RSD","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"HY63NN5Z","created_at":"2026-06-19T16:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HY63NN5ZNYZB5RSDIORDN6TEWN","target":"record","payload":{"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"},"canonical_sha256":"3e3db6b7b96e321ec64343a236fa64b36d1a4ac9709fba0aa3e1c0b0fe098353","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"},"source_kind":"arxiv","source_id":"2606.19544","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cElPQvVyRLsa9qfbuwRs4aNLNDoMd9dN1eGW+TeBoG83BHQnKBMpONjEE+hSsAL0O7lFRDW5/HON1P2FlSiTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:18:25.302172Z"},"content_sha256":"6090eb0ed0b04a16252b56ae29d6964a4cd9e3735110f31df107e6f3447a33a9","schema_version":"1.0","event_id":"sha256:6090eb0ed0b04a16252b56ae29d6964a4cd9e3735110f31df107e6f3447a33a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HY63NN5ZNYZB5RSDIORDN6TEWN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sgA6f2W0wqpUdavQuXlnEhrhR6U8ZH79hvTm+kLuBV6raQTlBq4bXsyGB9ljJtpHPYdTLjlm726KFP0peMgtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:18:25.302568Z"},"content_sha256":"cbb9aafe1993e363650cf76ad04b6f71ae2ae39929cd3d36d5a929c5cab0dd8e","schema_version":"1.0","event_id":"sha256:cbb9aafe1993e363650cf76ad04b6f71ae2ae39929cd3d36d5a929c5cab0dd8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/bundle.json","state_url":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T18:18:25Z","links":{"resolver":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN","bundle":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/bundle.json","state":"https://pith.science/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HY63NN5ZNYZB5RSDIORDN6TEWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HY63NN5ZNYZB5RSDIORDN6TEWN","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":"542aee541ed2f2ee7beef78a67cb92dc20ec8a804d0fa65dcdf83f9dc78935d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T19:37:13Z","title_canon_sha256":"7bafefce25b7c1d532538177eeefe8686e2f4faac974982217d6e1ddb48e7d03"},"schema_version":"1.0","source":{"id":"2606.19544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19544","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19544v1","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19544","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"HY63NN5ZNYZB","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"HY63NN5ZNYZB5RSD","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"HY63NN5Z","created_at":"2026-06-19T16:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:cbb9aafe1993e363650cf76ad04b6f71ae2ae39929cd3d36d5a929c5cab0dd8e","target":"graph","created_at":"2026-06-19T16:12:28Z","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/2606.19544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"D. Alex Hughes, Justin D. Norman, Michael U. Rivera","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T19:37:13Z","title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19544","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":"sha256:6090eb0ed0b04a16252b56ae29d6964a4cd9e3735110f31df107e6f3447a33a9","target":"record","created_at":"2026-06-19T16:12:28Z","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":"542aee541ed2f2ee7beef78a67cb92dc20ec8a804d0fa65dcdf83f9dc78935d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T19:37:13Z","title_canon_sha256":"7bafefce25b7c1d532538177eeefe8686e2f4faac974982217d6e1ddb48e7d03"},"schema_version":"1.0","source":{"id":"2606.19544","kind":"arxiv","version":1}},"canonical_sha256":"3e3db6b7b96e321ec64343a236fa64b36d1a4ac9709fba0aa3e1c0b0fe098353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e3db6b7b96e321ec64343a236fa64b36d1a4ac9709fba0aa3e1c0b0fe098353","first_computed_at":"2026-06-19T16:12:28.585399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:28.585399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAtxVnwkX74g2SzCHSlc5vuThEmBAn4S0QY3JNq9RFdz1+0NuZtvpUMfAJPOMuF/mIvAaodEp9cf/PLEnIBxAQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:28.585762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6090eb0ed0b04a16252b56ae29d6964a4cd9e3735110f31df107e6f3447a33a9","sha256:cbb9aafe1993e363650cf76ad04b6f71ae2ae39929cd3d36d5a929c5cab0dd8e"],"state_sha256":"39811e57bbeebf6a789ce6da5c95e1014d02dd9a43daa268102e6540fcd76a2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17z2o1wM7gAZsEiJw/7tjQGlN2WAkCpU8rLRn84YVKRAgOX2YCArgc5pl9nOg5bWBro7RIfQ7mVhD3tmxmpVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T18:18:25.305059Z","bundle_sha256":"0481e6edbc1701d2f06f23f3a30e808f421acbb75f387e7790740de90303eb89"}}