{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JKEB4AYWIAMZGAABW6R5U3PHC6","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":"e5edb23be7e909803fe6528d85fbaebddea1ef9841004e238f41e208c6ed6fee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T04:51:30Z","title_canon_sha256":"3c1d8ab0c04468e4259fa4e1f7d3808b34459951d7e75ff74ecfdc0f627f7530"},"schema_version":"1.0","source":{"id":"2503.05142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05142","created_at":"2026-07-05T10:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05142v1","created_at":"2026-07-05T10:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05142","created_at":"2026-07-05T10:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"JKEB4AYWIAMZ","created_at":"2026-07-05T10:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"JKEB4AYWIAMZGAAB","created_at":"2026-07-05T10:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"JKEB4AYW","created_at":"2026-07-05T10:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:117ac4bee0b69bf332a0edc063e53f0f44656415b9e5fc3762e6b3941072221a","target":"graph","created_at":"2026-07-05T10:26:21Z","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/2503.05142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) in diverse and challenging scenarios is essential to align them with human preferences. To mitigate the prohibitive costs associated with human evaluations, utilizing a powerful LLM as a judge has emerged as a favored approach. Nevertheless, this methodology encounters several challenges, including substantial expenses, concerns regarding privacy and security, and reproducibility. In this paper, we propose a straightforward, replicable, and accurate automated evaluation method by leveraging a lightweight LLM as the judge, named RocketEval. Initially, we ","authors_text":"Jianghong Ma, Ruizhi Qiao, Tianjun Wei, Wei Wen, Xing Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T04:51:30Z","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05142","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":"sha256:04450865356bc38ef48693998fa27cb46a46a4f3fb8e0050f228b0f098c6a17d","target":"record","created_at":"2026-07-05T10:26:21Z","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":"e5edb23be7e909803fe6528d85fbaebddea1ef9841004e238f41e208c6ed6fee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T04:51:30Z","title_canon_sha256":"3c1d8ab0c04468e4259fa4e1f7d3808b34459951d7e75ff74ecfdc0f627f7530"},"schema_version":"1.0","source":{"id":"2503.05142","kind":"arxiv","version":1}},"canonical_sha256":"4a881e03164019930001b7a3da6de71787440850cfafaa29f367f0458dd2e256","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a881e03164019930001b7a3da6de71787440850cfafaa29f367f0458dd2e256","first_computed_at":"2026-07-05T10:26:21.778976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:21.778976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zIwEvhF2d6WqD6hE0YQmeWL5k47O1Lvb8jZRcGXEA8WwI0aYoauMrQhmR6PX6v+YfbuzR2CyHX8t0hR8M3QnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:21.779389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04450865356bc38ef48693998fa27cb46a46a4f3fb8e0050f228b0f098c6a17d","sha256:117ac4bee0b69bf332a0edc063e53f0f44656415b9e5fc3762e6b3941072221a"],"state_sha256":"1990ee0ae055abd6103917ddf7b59bec8f03f85d740d3dc3d74001bdd61f79cc"}