{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VHUKO2FRS5VB3K24CAJBKZP2OU","short_pith_number":"pith:VHUKO2FR","schema_version":"1.0","canonical_sha256":"a9e8a768b1976a1dab5c10121565fa75185c4458a622a42b6e4e15498193aa13","source":{"kind":"arxiv","id":"2410.11594","version":1},"attestation_state":"computed","paper":{"title":"Black-box Uncertainty Quantification Method for LLM-as-a-Judge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","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","submitted_at":"2024-10-15T13:29:22Z","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"},"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":"2410.11594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T13:29:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf9483ce00da804308bbabb7f65f12491d51fc5b6ce18c33236d9b7759ebb29e","abstract_canon_sha256":"3318e6076144c1aaf1d09f84d252030750096378393fbeb0f9ee174ecad204cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:56.287745Z","signature_b64":"y8MBrkfKp+PDOF5ZvbKG4+y3u14i6WwBAJzbaVTRK+Dn/hUThVA5Ret84JqYA0fLYXuhCZH5FDp8qPDn3JGyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e8a768b1976a1dab5c10121565fa75185c4458a622a42b6e4e15498193aa13","last_reissued_at":"2026-07-05T09:20:56.287255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:56.287255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black-box Uncertainty Quantification Method for LLM-as-a-Judge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","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","submitted_at":"2024-10-15T13:29:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11594","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/2410.11594/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":"2410.11594","created_at":"2026-07-05T09:20:56.287326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11594v1","created_at":"2026-07-05T09:20:56.287326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11594","created_at":"2026-07-05T09:20:56.287326+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHUKO2FRS5VB","created_at":"2026-07-05T09:20:56.287326+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHUKO2FRS5VB3K24","created_at":"2026-07-05T09:20:56.287326+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHUKO2FR","created_at":"2026-07-05T09:20:56.287326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.27106","citing_title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25235","citing_title":"VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU","json":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU.json","graph_json":"https://pith.science/api/pith-number/VHUKO2FRS5VB3K24CAJBKZP2OU/graph.json","events_json":"https://pith.science/api/pith-number/VHUKO2FRS5VB3K24CAJBKZP2OU/events.json","paper":"https://pith.science/paper/VHUKO2FR"},"agent_actions":{"view_html":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU","download_json":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU.json","view_paper":"https://pith.science/paper/VHUKO2FR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11594&json=true","fetch_graph":"https://pith.science/api/pith-number/VHUKO2FRS5VB3K24CAJBKZP2OU/graph.json","fetch_events":"https://pith.science/api/pith-number/VHUKO2FRS5VB3K24CAJBKZP2OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU/action/storage_attestation","attest_author":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU/action/author_attestation","sign_citation":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU/action/citation_signature","submit_replication":"https://pith.science/pith/VHUKO2FRS5VB3K24CAJBKZP2OU/action/replication_record"}},"created_at":"2026-07-05T09:20:56.287326+00:00","updated_at":"2026-07-05T09:20:56.287326+00:00"}