{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UAXYNKYT7GM7UTCICB42FWCP4Y","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":"6ee3c8e9afe93fa87296e04c5f0e720c74a79d45d81aad00ec38106335484ecc","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T08:16:18Z","title_canon_sha256":"1814b3f47cffabdfdc2254008974790daf9f6395b832294b0dd844f8e4192192"},"schema_version":"1.0","source":{"id":"2505.15240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15240","created_at":"2026-07-05T11:06:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15240v1","created_at":"2026-07-05T11:06:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15240","created_at":"2026-07-05T11:06:42Z"},{"alias_kind":"pith_short_12","alias_value":"UAXYNKYT7GM7","created_at":"2026-07-05T11:06:42Z"},{"alias_kind":"pith_short_16","alias_value":"UAXYNKYT7GM7UTCI","created_at":"2026-07-05T11:06:42Z"},{"alias_kind":"pith_short_8","alias_value":"UAXYNKYT","created_at":"2026-07-05T11:06:42Z"}],"graph_snapshots":[{"event_id":"sha256:be48c7009eaa8936825d6cbd0104b7bea617dd5abf90def55122cfef93cee270","target":"graph","created_at":"2026-07-05T11:06:42Z","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/2505.15240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores generalised probabilistic modelling and uncertainty estimation in comparative LLM-as-a-judge frameworks. We show that existing Product-of-Experts methods are specific cases of a broader framework, enabling diverse modelling options. Furthermore, we propose improved uncertainty estimates for individual comparisons, enabling more efficient selection and achieving strong performance with fewer evaluations. We also introduce a method for estimating overall ranking uncertainty. Finally, we demonstrate that combining absolute and comparative scoring improves performance. Experime","authors_text":"Mark J. F. Gales, Yassir Fathullah","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T08:16:18Z","title":"Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15240","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":"sha256:27b38c21cf6a5eebb3b953635a65c2f5b52b7345bb711ebd03659d578f603cbd","target":"record","created_at":"2026-07-05T11:06:42Z","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":"6ee3c8e9afe93fa87296e04c5f0e720c74a79d45d81aad00ec38106335484ecc","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T08:16:18Z","title_canon_sha256":"1814b3f47cffabdfdc2254008974790daf9f6395b832294b0dd844f8e4192192"},"schema_version":"1.0","source":{"id":"2505.15240","kind":"arxiv","version":1}},"canonical_sha256":"a02f86ab13f999fa4c481079a2d84fe6338d72852dc735efdc7b97ab38f1b6d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a02f86ab13f999fa4c481079a2d84fe6338d72852dc735efdc7b97ab38f1b6d6","first_computed_at":"2026-07-05T11:06:42.593113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:42.593113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x+J1Bcs6CtZR1Ja0Tp/N3OVZDcb/l9zPNZownyByc1Gwy4XuRvPUaUo/4K8BKGbbJOCCXCOJkPV0qWVhq5wuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:42.593609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27b38c21cf6a5eebb3b953635a65c2f5b52b7345bb711ebd03659d578f603cbd","sha256:be48c7009eaa8936825d6cbd0104b7bea617dd5abf90def55122cfef93cee270"],"state_sha256":"fd36c629334584218675514dc0d8d276a2bc42b1ed053f456d02ab65568850a1"}