{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3IYOCLTWTGCJ4JECL5MJK3N6LN","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":"3c0145f9067668111c5f22e52e90203e95cb06bca1aca03b4c094b14a74909ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T16:58:36Z","title_canon_sha256":"55db84d8f3374f30a2222d76a0acdf325d48af4435d19703883580cebb001540"},"schema_version":"1.0","source":{"id":"2411.07127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07127","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07127v2","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07127","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"3IYOCLTWTGCJ","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"3IYOCLTWTGCJ4JEC","created_at":"2026-07-05T10:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"3IYOCLTW","created_at":"2026-07-05T10:55:25Z"}],"graph_snapshots":[{"event_id":"sha256:3a0705052aea9fe6953ee9751d45306adbbe1f2effa9712053df4ca44c2e0a8a","target":"graph","created_at":"2026-07-05T10:55:25Z","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/2411.07127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by Large Language Models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review.\n  GEM uses a generative model to estimate mutual information between","authors_text":"Grant Schoenebeck, Shengwei Xu, Yuqing Kong, Yuxuan Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T16:58:36Z","title":"Benchmarking LLMs' Judgments with No Gold Standard"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07127","kind":"arxiv","version":2},"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":"sha256:1d68e5d952546a81d356ca5d0bb4479d8f45fd896fb1d7eee1b6a0dee4288238","target":"record","created_at":"2026-07-05T10:55:25Z","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":"3c0145f9067668111c5f22e52e90203e95cb06bca1aca03b4c094b14a74909ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T16:58:36Z","title_canon_sha256":"55db84d8f3374f30a2222d76a0acdf325d48af4435d19703883580cebb001540"},"schema_version":"1.0","source":{"id":"2411.07127","kind":"arxiv","version":2}},"canonical_sha256":"da30e12e7699849e24825f58956dbe5b70b7bbc4ec3ed7da9cdd2bc1bb4552b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da30e12e7699849e24825f58956dbe5b70b7bbc4ec3ed7da9cdd2bc1bb4552b3","first_computed_at":"2026-07-05T10:55:25.831405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:25.831405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hHIiJ4qodihHLvZj8aS4BM7G5TOYCUmWwPAfbKIUf7NYTFJV0R6XxcYHdVravAxGjo2jxyUbPlyAJjxtaSDtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:25.831891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d68e5d952546a81d356ca5d0bb4479d8f45fd896fb1d7eee1b6a0dee4288238","sha256:3a0705052aea9fe6953ee9751d45306adbbe1f2effa9712053df4ca44c2e0a8a"],"state_sha256":"5430ef469f3ec9ce33bf2ad91443b158c8bb7f8c222b93b8e89b8a1cd1edb166"}