{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TLNZG57L5SUHPYIYXN7HEWKXZ2","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":"41d49df5c64c2f7a38fc559209f8814eb4705abc2797d001a11d3f95ff73469d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:43:26Z","title_canon_sha256":"0eb38fe1dedf9c42ab3c44327668833144f65815f1282eadf83a2489c483a60c"},"schema_version":"1.0","source":{"id":"2311.09766","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09766","created_at":"2026-07-05T08:28:35Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09766v4","created_at":"2026-07-05T08:28:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09766","created_at":"2026-07-05T08:28:35Z"},{"alias_kind":"pith_short_12","alias_value":"TLNZG57L5SUH","created_at":"2026-07-05T08:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"TLNZG57L5SUHPYIY","created_at":"2026-07-05T08:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"TLNZG57L","created_at":"2026-07-05T08:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:f2e02659a701c963b4a33cbba60f56c86c40dbde3439cac81dbe60f6d7e6bb63","target":"graph","created_at":"2026-07-05T08:28:35Z","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/2311.09766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic evaluation of generated textual content presents an ongoing challenge within the field of NLP. Given the impressive capabilities of modern language models (LMs) across diverse NLP tasks, there is a growing trend to employ these models in creating innovative evaluation metrics for automated assessment of generation tasks. This paper investigates a pivotal question: Do language model-driven evaluation metrics inherently exhibit bias favoring texts generated by the same underlying language model? Specifically, we assess whether prominent LM-based evaluation metrics (e.g. BARTScore, T5Sc","authors_text":"Chenghua Lin, Nafise Sadat Moosavi, Yiqi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:43:26Z","title":"LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09766","kind":"arxiv","version":4},"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":"sha256:6259a1c30dc8e8201382234c68e940b293803e67d8ce85efef6e38b787611dc5","target":"record","created_at":"2026-07-05T08:28:35Z","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":"41d49df5c64c2f7a38fc559209f8814eb4705abc2797d001a11d3f95ff73469d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:43:26Z","title_canon_sha256":"0eb38fe1dedf9c42ab3c44327668833144f65815f1282eadf83a2489c483a60c"},"schema_version":"1.0","source":{"id":"2311.09766","kind":"arxiv","version":4}},"canonical_sha256":"9adb9377ebeca877e118bb7e725957ce881de4c7bf4fd904c1b98d2b27cab28c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9adb9377ebeca877e118bb7e725957ce881de4c7bf4fd904c1b98d2b27cab28c","first_computed_at":"2026-07-05T08:28:35.247102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:35.247102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RlH0G7Ddgbbg6WxQay9T8/1Fswxz66y73fv5zS/y6nnEAqEZrujtfJfY9SLQD6im+SN+IVkk3G0IA6E+hQk6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:35.247598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09766","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6259a1c30dc8e8201382234c68e940b293803e67d8ce85efef6e38b787611dc5","sha256:f2e02659a701c963b4a33cbba60f56c86c40dbde3439cac81dbe60f6d7e6bb63"],"state_sha256":"6a90317d2fceb08313c5b4cd99402e7f6c966ed3de0e29746b4b8bfc1b37a174"}