{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGZAL2L3FUHAB3UUBPDWNMAARP","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":"6bd7e0ccc6931acdc636713f738c34656890f298666b57bec06d55d67e9a0d02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:40:02Z","title_canon_sha256":"ee6407c24552a112819d93a93390bd5420009d9ff0d3c13e1aa3afcc8010c40f"},"schema_version":"1.0","source":{"id":"2409.11239","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11239","created_at":"2026-07-05T09:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11239v2","created_at":"2026-07-05T09:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11239","created_at":"2026-07-05T09:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"JGZAL2L3FUHA","created_at":"2026-07-05T09:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"JGZAL2L3FUHAB3UU","created_at":"2026-07-05T09:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"JGZAL2L3","created_at":"2026-07-05T09:14:38Z"}],"graph_snapshots":[{"event_id":"sha256:60b47ae44a54c76c2a157db73d18359f8f08e648f211ad8c149f2b521e255755","target":"graph","created_at":"2026-07-05T09:14:38Z","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/2409.11239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-a-Judge and reward models are widely used alternatives of multiple-choice questions or human annotators for large language model (LLM) evaluation. Their efficacy shines in evaluating long-form responses, serving a critical role as evaluators of leaderboards and as proxies to align LLMs via reinforcement learning. However, despite their popularity, their effectiveness in diverse contexts, such as non-English prompts, factual verification, or challenging questions, remains unexplored. In this paper, we conduct a comprehensive analysis of automated evaluators, reporting several key finding","authors_text":"Guijin Son, Hoyoung Lee, Hyunwoo Ko, Seunghyeok Hong, Yewon Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:40:02Z","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11239","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":"sha256:168e627e43ea5b878d951ede3014957abbe121d289c9c4e34ae3d6fcc34a946f","target":"record","created_at":"2026-07-05T09:14:38Z","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":"6bd7e0ccc6931acdc636713f738c34656890f298666b57bec06d55d67e9a0d02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:40:02Z","title_canon_sha256":"ee6407c24552a112819d93a93390bd5420009d9ff0d3c13e1aa3afcc8010c40f"},"schema_version":"1.0","source":{"id":"2409.11239","kind":"arxiv","version":2}},"canonical_sha256":"49b205e97b2d0e00ee940bc766b0008bebd7bcb2a754dece5b442d0e71cc3df5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49b205e97b2d0e00ee940bc766b0008bebd7bcb2a754dece5b442d0e71cc3df5","first_computed_at":"2026-07-05T09:14:38.522592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:38.522592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"43e99WFB/ArxrMWW3UwK/bCSjWZO0uHxK4XwC1SAtALhlkgKxq3Mhcmz4xT2QT0BrGuWBqBb9v/pcCGhs8dbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:38.523023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11239","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:168e627e43ea5b878d951ede3014957abbe121d289c9c4e34ae3d6fcc34a946f","sha256:60b47ae44a54c76c2a157db73d18359f8f08e648f211ad8c149f2b521e255755"],"state_sha256":"d7480bb54c85850af2428c4547f1e7e92991729b24d6b4f595ae6259fb92b39f"}