{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4Y6GWTBVLMNS7HTUKCEV24KJHC","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":"2bf427d896b22ae7ef4e2b08cb542df028f8acabc10c03ed0550a11ee6f58c96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-10T09:15:19Z","title_canon_sha256":"d1c16b235e3e56dda7f32f96fa79f3314c59959aa655ab914ca622050f8c1a57"},"schema_version":"1.0","source":{"id":"2603.09403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09403","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09403v2","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09403","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"4Y6GWTBVLMNS","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"4Y6GWTBVLMNS7HTU","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"4Y6GWTBV","created_at":"2026-06-02T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:af049a495704e842ae1c476854732b286f3a3134e264a5b20d860e375098785c","target":"graph","created_at":"2026-06-02T01:03:45Z","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/2603.09403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Validating evaluation metrics for NLG typically relies on expensive and time-consuming human annotations, which predominantly exist only for English datasets. We propose LLM as a Meta-Judge, a scalable framework that utilizes LLMs to generate synthetic evaluation datasets via controlled semantic degradation of real data, replacing human judgment. We validate our approach using \\textit{meta-correlation}, measuring the alignment between metric rankings derived from synthetic data and those from standard human benchmarks. Experiments across Machine Translation, Question Answering, and Summarizati","authors_text":"David Hurych, Jind\\v{r}ich Libovick\\'y, Luk\\'a\\v{s} Eigler","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-10T09:15:19Z","title":"LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09403","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":"sha256:09df5171427e11754133edf0b81c51d73171b88991e5342d3059a0aa4f1d3fe7","target":"record","created_at":"2026-06-02T01:03:45Z","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":"2bf427d896b22ae7ef4e2b08cb542df028f8acabc10c03ed0550a11ee6f58c96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-10T09:15:19Z","title_canon_sha256":"d1c16b235e3e56dda7f32f96fa79f3314c59959aa655ab914ca622050f8c1a57"},"schema_version":"1.0","source":{"id":"2603.09403","kind":"arxiv","version":2}},"canonical_sha256":"e63c6b4c355b1b2f9e7450895d714938838a68f5b861cd7e7c47b40165760929","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e63c6b4c355b1b2f9e7450895d714938838a68f5b861cd7e7c47b40165760929","first_computed_at":"2026-06-02T01:03:45.279330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:45.279330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/RmJrgtwrTsd9hJoUzj1aRvYfhP2z3Z8vFLIDpDeB2XFYWcGYGOYiXpalRTd21c38iUGdZl7aSIhBXhEx9zhCg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:45.279855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.09403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09df5171427e11754133edf0b81c51d73171b88991e5342d3059a0aa4f1d3fe7","sha256:af049a495704e842ae1c476854732b286f3a3134e264a5b20d860e375098785c"],"state_sha256":"eed0459ff950990ebba5d23961c6f6eccd67a2c05bbcf44afae8e9b6b8167149"}