{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SJGN4FBPMO4AKGUCH3S7AXF7BY","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":"c25932d1a8dd0b93340164f0e3d6d5570f67f3571aa057b4ce05c2fb70aeae70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T20:42:28Z","title_canon_sha256":"210f4b7479ec1faade9a13d31c371340ad5fc31059309384edd2c6aea2b4c9b5"},"schema_version":"1.0","source":{"id":"2405.01724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01724","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01724v1","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01724","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"SJGN4FBPMO4A","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"SJGN4FBPMO4AKGUC","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"SJGN4FBP","created_at":"2026-07-05T08:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:0a1e5f6cf875a5f84433d800e9177aeeef2f5e776ac4c63493089e0b017c0301","target":"graph","created_at":"2026-07-05T08:15:01Z","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/2405.01724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The zero-shot capability of Large Language Models (LLMs) has enabled highly flexible, reference-free metrics for various tasks, making LLM evaluators common tools in NLP. However, the robustness of these LLM evaluators remains relatively understudied; existing work mainly pursued optimal performance in terms of correlating LLM scores with human expert scores. In this paper, we conduct a series of analyses using the SummEval dataset and confirm that LLMs are biased evaluators as they: (1) exhibit familiarity bias-a preference for text with lower perplexity, (2) show skewed and biased distributi","authors_text":"Dimitris Alikaniotis, Rickard Stureborg, Yoshi Suhara","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T20:42:28Z","title":"Large Language Models are Inconsistent and Biased Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01724","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":"sha256:59de9b89b84445ccc81f77312fdc0b5f7b5946a3d828412dca76c8de7eff0d53","target":"record","created_at":"2026-07-05T08:15:01Z","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":"c25932d1a8dd0b93340164f0e3d6d5570f67f3571aa057b4ce05c2fb70aeae70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T20:42:28Z","title_canon_sha256":"210f4b7479ec1faade9a13d31c371340ad5fc31059309384edd2c6aea2b4c9b5"},"schema_version":"1.0","source":{"id":"2405.01724","kind":"arxiv","version":1}},"canonical_sha256":"924cde142f63b8051a823ee5f05cbf0e311c0bfb6d4c70c5f7f5206f3fcafd61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"924cde142f63b8051a823ee5f05cbf0e311c0bfb6d4c70c5f7f5206f3fcafd61","first_computed_at":"2026-07-05T08:15:01.208754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:01.208754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fd0SBZeJjWATY6A1gDDocqt1xvWrHZ+JFRhSnTbrgvyyBcd4gsgwwVGx9TowA8XCVE7jDryR8jNiAnR/NDcTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:01.209170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59de9b89b84445ccc81f77312fdc0b5f7b5946a3d828412dca76c8de7eff0d53","sha256:0a1e5f6cf875a5f84433d800e9177aeeef2f5e776ac4c63493089e0b017c0301"],"state_sha256":"18709167c92d6d08acf3fc6745ccd66db35c2f1a6db6cb70a34248ffb87237c2"}