{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VHUKO2FRS5VB3K24CAJBKZP2OU","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":"3318e6076144c1aaf1d09f84d252030750096378393fbeb0f9ee174ecad204cd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T13:29:22Z","title_canon_sha256":"bf9483ce00da804308bbabb7f65f12491d51fc5b6ce18c33236d9b7759ebb29e"},"schema_version":"1.0","source":{"id":"2410.11594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11594","created_at":"2026-07-05T09:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11594v1","created_at":"2026-07-05T09:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11594","created_at":"2026-07-05T09:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"VHUKO2FRS5VB","created_at":"2026-07-05T09:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"VHUKO2FRS5VB3K24","created_at":"2026-07-05T09:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"VHUKO2FR","created_at":"2026-07-05T09:20:56Z"}],"graph_snapshots":[{"event_id":"sha256:712b65d244cb933917d5a0cf37992b2494348b4ceccfb75bd35e2573a84f5da3","target":"graph","created_at":"2026-07-05T09:20:56Z","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/2410.11594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-a-Judge is a widely used method for evaluating the performance of Large Language Models (LLMs) across various tasks. We address the challenge of quantifying the uncertainty of LLM-as-a-Judge evaluations. While uncertainty quantification has been well-studied in other domains, applying it effectively to LLMs poses unique challenges due to their complex decision-making capabilities and computational demands. In this paper, we introduce a novel method for quantifying uncertainty designed to enhance the trustworthiness of LLM-as-a-Judge evaluations. The method quantifies uncertainty by anal","authors_text":"Elizabeth M. Daly, James M. Johnson, Mart\\'in Santill\\'an Cooper, Michael Desmond, Nico Wagner, Qian Pan, Rahul Nair, Werner Geyer, Zahra Ashktorab","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T13:29:22Z","title":"Black-box Uncertainty Quantification Method for LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11594","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":"sha256:5f25ff5a61654c84f8cd17b9ca92023363de553a10d896a64f9684a33e787c33","target":"record","created_at":"2026-07-05T09:20:56Z","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":"3318e6076144c1aaf1d09f84d252030750096378393fbeb0f9ee174ecad204cd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T13:29:22Z","title_canon_sha256":"bf9483ce00da804308bbabb7f65f12491d51fc5b6ce18c33236d9b7759ebb29e"},"schema_version":"1.0","source":{"id":"2410.11594","kind":"arxiv","version":1}},"canonical_sha256":"a9e8a768b1976a1dab5c10121565fa75185c4458a622a42b6e4e15498193aa13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9e8a768b1976a1dab5c10121565fa75185c4458a622a42b6e4e15498193aa13","first_computed_at":"2026-07-05T09:20:56.287255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:56.287255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y8MBrkfKp+PDOF5ZvbKG4+y3u14i6WwBAJzbaVTRK+Dn/hUThVA5Ret84JqYA0fLYXuhCZH5FDp8qPDn3JGyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:56.287745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f25ff5a61654c84f8cd17b9ca92023363de553a10d896a64f9684a33e787c33","sha256:712b65d244cb933917d5a0cf37992b2494348b4ceccfb75bd35e2573a84f5da3"],"state_sha256":"248f93fd38e263347c570f28a4ebf872aaca711e6aafebf0c3bb00e6a54ceffb"}