{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z27MCPDXT2UFJ4AUFXJLAIDBD6","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":"3b2c21b6634326084e69068299e4364f439b8b6f4c1db37e25215835f9556e4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:30:13Z","title_canon_sha256":"c2b8a1e6ef3056aca83499d1a5a623f3d3b7591b324e4ed48f7ed09087988748"},"schema_version":"1.0","source":{"id":"2405.11874","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11874","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11874v3","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11874","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"Z27MCPDXT2UF","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"Z27MCPDXT2UFJ4AU","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"Z27MCPDX","created_at":"2026-07-05T10:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:2253db9274128e3e7a5a6af2b80095f269112e5b0f7189fb4de74f6a4a706547","target":"graph","created_at":"2026-07-05T10:19:24Z","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/2405.11874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The continuous advancement of large language models (LLMs) has brought increasing attention to the critical issue of developing fair and reliable methods for evaluating their performance. Particularly, the emergence of cheating phenomena, such as test set leakage and prompt format overfitting, poses significant challenges to the reliable evaluation of LLMs. As evaluation frameworks commonly use Regular Expression (RegEx) for answer extraction, models may adjust their responses to fit formats easily handled by RegEx. Nevertheless, the key answer extraction module based on RegEx frequently suffe","authors_text":"Bo Tang, Ding Chen, Feiyu Xiong, Qingchen Yu, Shichao Song, Zhiyu Li, Zifan Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:30:13Z","title":"xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11874","kind":"arxiv","version":3},"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:f94b748d9e81c6956374c92a2d81c9d70b0f207c77aa313c7a4e935834d52579","target":"record","created_at":"2026-07-05T10:19:24Z","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":"3b2c21b6634326084e69068299e4364f439b8b6f4c1db37e25215835f9556e4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:30:13Z","title_canon_sha256":"c2b8a1e6ef3056aca83499d1a5a623f3d3b7591b324e4ed48f7ed09087988748"},"schema_version":"1.0","source":{"id":"2405.11874","kind":"arxiv","version":3}},"canonical_sha256":"cebec13c779ea854f0142dd2b020611fb791cf8c7c014defd2fd26a26fafa70d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cebec13c779ea854f0142dd2b020611fb791cf8c7c014defd2fd26a26fafa70d","first_computed_at":"2026-07-05T10:19:24.109302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:24.109302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0oyXE/0tD7p9b6ZlM52SS4GtGiU9Lu0aYf6BytEuxJ06WoN9YJMlOlG0QJQffM0/9ptHvxeeld8Czl49dWkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:24.109829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11874","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f94b748d9e81c6956374c92a2d81c9d70b0f207c77aa313c7a4e935834d52579","sha256:2253db9274128e3e7a5a6af2b80095f269112e5b0f7189fb4de74f6a4a706547"],"state_sha256":"c5df5b26d2291498ccbd382fe2b1303fc952174f6b818beb351031f987cdfbf0"}