{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TZIDFD6SLGDBX5JY7ETKB7GBMB","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":"e25fac0f9275ea356fd9306ecb5f54b8c82a4baf5581cfbd853f2d052d0c149e","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T05:05:03Z","title_canon_sha256":"558af87828a216b6fa7c43d9a6b6f947cf1d8195c559b3b804ed5f2e08c21bbb"},"schema_version":"1.0","source":{"id":"2303.13809","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13809","created_at":"2026-07-05T08:27:40Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13809v4","created_at":"2026-07-05T08:27:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13809","created_at":"2026-07-05T08:27:40Z"},{"alias_kind":"pith_short_12","alias_value":"TZIDFD6SLGDB","created_at":"2026-07-05T08:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"TZIDFD6SLGDBX5JY","created_at":"2026-07-05T08:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"TZIDFD6S","created_at":"2026-07-05T08:27:40Z"}],"graph_snapshots":[{"event_id":"sha256:7692cef105d15f7e22ed81fc436ad809c1b86dd4630322de83dfab26ac291180","target":"graph","created_at":"2026-07-05T08:27:40Z","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/2303.13809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative large language models (LLMs), e.g., ChatGPT, have demonstrated remarkable proficiency across several NLP tasks, such as machine translation, text summarization. Recent research (Kocmi and Federmann, 2023) has shown that utilizing LLMs for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level but \\textit{performs poorly at the segment level}. To further improve the performance of LLMs on MT quality assessment, we investigate several prompting designs, and propose a new prompting method called \\textbf{\\texttt{Error Analysis Prompti","authors_text":"Baopu Qiu, Dacheng Tao, Kanjian Zhang, Liang Ding, Qingyu Lu, Tom Kocmi","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T05:05:03Z","title":"Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13809","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":"sha256:9918cdb3c412ff8cb4b9afe05f65301d251665869b56ae6a4dd055a7cb6cb935","target":"record","created_at":"2026-07-05T08:27:40Z","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":"e25fac0f9275ea356fd9306ecb5f54b8c82a4baf5581cfbd853f2d052d0c149e","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T05:05:03Z","title_canon_sha256":"558af87828a216b6fa7c43d9a6b6f947cf1d8195c559b3b804ed5f2e08c21bbb"},"schema_version":"1.0","source":{"id":"2303.13809","kind":"arxiv","version":4}},"canonical_sha256":"9e50328fd259861bf538f926a0fcc160678e76838d48d7c029e17bbf13b62f70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e50328fd259861bf538f926a0fcc160678e76838d48d7c029e17bbf13b62f70","first_computed_at":"2026-07-05T08:27:40.201474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:40.201474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J+RB+MfmbefwzIE5r64r14KWkur1WpGnEo087f7gnt00BeLi3loEDIOA0r/HchZ045D737ZzEXvJRKvMMqssAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:40.201943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13809","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9918cdb3c412ff8cb4b9afe05f65301d251665869b56ae6a4dd055a7cb6cb935","sha256:7692cef105d15f7e22ed81fc436ad809c1b86dd4630322de83dfab26ac291180"],"state_sha256":"16557b4bf8f273cd0b0ac64f487390e4aa4c91232630f075b971008c113e6541"}