{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LNHMUG26CGVS6IHCLIN6FCCEEJ","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":"001b76e1b5fadc5cba2bfc2fc69b1edcf6ac5bf56b089fbb1170b4ada2d0ed3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-15T22:02:12Z","title_canon_sha256":"e3cada5d2c4f530201d8e5298b81670289974b1138485707f8ed8b170ec0adc1"},"schema_version":"1.0","source":{"id":"2307.07889","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07889","created_at":"2026-07-05T07:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07889v3","created_at":"2026-07-05T07:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07889","created_at":"2026-07-05T07:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"LNHMUG26CGVS","created_at":"2026-07-05T07:41:41Z"},{"alias_kind":"pith_short_16","alias_value":"LNHMUG26CGVS6IHC","created_at":"2026-07-05T07:41:41Z"},{"alias_kind":"pith_short_8","alias_value":"LNHMUG26","created_at":"2026-07-05T07:41:41Z"}],"graph_snapshots":[{"event_id":"sha256:d1966cc80060ff89783cf26fa21e89c5ec85d0bea3860970513c9a0250772ff6","target":"graph","created_at":"2026-07-05T07:41:41Z","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/2307.07889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these systems is in the automated assessment of natural language generation (NLG), a highly challenging area with great practical benefit. In this paper, we explore two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment: absolute score prediction, and comparative assessment which uses relative comparisons between pairs of candidates. Though comparative assessment has not been extensively studied ","authors_text":"Adian Liusie, Mark J. F. Gales, Potsawee Manakul","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-15T22:02:12Z","title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07889","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":"sha256:9d86fb7b62fd0fb8827fc101a1a09f340e47c0c3caa0cfdfd95f1bca08e79a97","target":"record","created_at":"2026-07-05T07:41:41Z","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":"001b76e1b5fadc5cba2bfc2fc69b1edcf6ac5bf56b089fbb1170b4ada2d0ed3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-15T22:02:12Z","title_canon_sha256":"e3cada5d2c4f530201d8e5298b81670289974b1138485707f8ed8b170ec0adc1"},"schema_version":"1.0","source":{"id":"2307.07889","kind":"arxiv","version":3}},"canonical_sha256":"5b4eca1b5e11ab2f20e25a1be288442255d30d45d260ca52316dfc1e3651bab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b4eca1b5e11ab2f20e25a1be288442255d30d45d260ca52316dfc1e3651bab2","first_computed_at":"2026-07-05T07:41:41.462693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:41.462693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CoYhYwiVSSEMUfYI2nbvCMSG0VbEi+cnk3NZJ3frZDrj9FMIFM12I9Pq2whjU+jJHbTHjLGSlZ+INvFjaG3/Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:41.463111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07889","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d86fb7b62fd0fb8827fc101a1a09f340e47c0c3caa0cfdfd95f1bca08e79a97","sha256:d1966cc80060ff89783cf26fa21e89c5ec85d0bea3860970513c9a0250772ff6"],"state_sha256":"c7fc7c21f3f5eb25b322a5a86466b22fce7f51ca2da2e9ce8c2cb0871059fa39"}