{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EGPQISGQSIEUUWDKLFUEKGZXCI","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":"be7b7877e59aa199eb52028c32047114fe98655b16e74d032ccfec2fb1344a98","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T17:33:23Z","title_canon_sha256":"588ff1f300b4f69de07667a02b5126fbe2d306c7a040cad27c1bcd88e3c9df17"},"schema_version":"1.0","source":{"id":"2504.15253","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15253","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15253v2","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15253","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"EGPQISGQSIEU","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"EGPQISGQSIEUUWDK","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"EGPQISGQ","created_at":"2026-07-05T11:07:23Z"}],"graph_snapshots":[{"event_id":"sha256:188133723ac31b2c9dd28a9070f9e74aed0a8b8864834234b86a1fb57a6c503e","target":"graph","created_at":"2026-07-05T11:07:23Z","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/2504.15253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling test-time computation, or affording a generator large language model (LLM) extra compute during inference, typically employs the help of external non-generative evaluators (i.e., reward models). Concurrently, LLM-judges, models trained to generate evaluations and critiques (explanations) in natural language, are becoming increasingly popular in automatic evaluation. Despite judge empirical successes, their effectiveness as evaluators in test-time scaling settings is largely unknown. In this paper, we introduce the Judge Evaluation for Test-Time Scaling (JETTS) benchmark, which evaluate","authors_text":"Austin Xu, Caiming Xiong, Peifeng Wang, Shafiq Joty, Yilun Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T17:33:23Z","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15253","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:a360bb84e05c69060ae36fb29ea06e21162db37875b5ccf2e7d683cc575b6f54","target":"record","created_at":"2026-07-05T11:07:23Z","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":"be7b7877e59aa199eb52028c32047114fe98655b16e74d032ccfec2fb1344a98","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T17:33:23Z","title_canon_sha256":"588ff1f300b4f69de07667a02b5126fbe2d306c7a040cad27c1bcd88e3c9df17"},"schema_version":"1.0","source":{"id":"2504.15253","kind":"arxiv","version":2}},"canonical_sha256":"219f0448d092094a586a5968451b37122f9f6d9850f090a3e5330f64046d9799","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"219f0448d092094a586a5968451b37122f9f6d9850f090a3e5330f64046d9799","first_computed_at":"2026-07-05T11:07:23.881696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:23.881696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kh/UWsEJx4JTxRdyUb5RWDFSyLqqJ3KYSm+otvY8cCSY9UTI45Jwzde5uGG4ZfdTEPFUhxy30qDhqE6wEUQGCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:23.882176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15253","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a360bb84e05c69060ae36fb29ea06e21162db37875b5ccf2e7d683cc575b6f54","sha256:188133723ac31b2c9dd28a9070f9e74aed0a8b8864834234b86a1fb57a6c503e"],"state_sha256":"b20afd4d7f5e9310a74f80d68d935032d82ffe5ee4f35e7f8088ef38f6cfa462"}