{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MGBCFU5PUXGPRXGION6R5OINEP","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":"6e839c82dc18a04d378bab8cc701e7e7d4c0cdc98b4436479b35a9e89b5f734a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T12:31:44Z","title_canon_sha256":"0fe355795fa4af62c0938765d615f9b062cf6b9b63f383cc1a5e8ef3ebbaa667"},"schema_version":"1.0","source":{"id":"2406.09972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09972","created_at":"2026-07-05T08:37:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09972v1","created_at":"2026-07-05T08:37:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09972","created_at":"2026-07-05T08:37:20Z"},{"alias_kind":"pith_short_12","alias_value":"MGBCFU5PUXGP","created_at":"2026-07-05T08:37:20Z"},{"alias_kind":"pith_short_16","alias_value":"MGBCFU5PUXGPRXGI","created_at":"2026-07-05T08:37:20Z"},{"alias_kind":"pith_short_8","alias_value":"MGBCFU5P","created_at":"2026-07-05T08:37:20Z"}],"graph_snapshots":[{"event_id":"sha256:e3c7f4f85975e33787284620eda590a936a11e181cb3e8c3e856d99215f1a061","target":"graph","created_at":"2026-07-05T08:37:20Z","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/2406.09972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research investigates prompt designs of evaluating generated texts using large language models (LLMs). While LLMs are increasingly used for scoring various inputs, creating effective prompts for open-ended text evaluation remains challenging due to model sensitivity and subjectivity in evaluation of text generation. Our study experimented with different prompt structures, altering the sequence of output instructions and including explanatory reasons. We found that the order of presenting reasons and scores significantly influences LLMs' scoring, with a different level of rule understandin","authors_text":"Hideki Nakayama, KuanChao Chu, Yi-Pei Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T12:31:44Z","title":"A Better LLM Evaluator for Text Generation: The Impact of Prompt Output Sequencing and Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09972","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":"sha256:796a0d67aace8c512a2b9bdad01b2545cdb73240af828fbc6434b23c03f35551","target":"record","created_at":"2026-07-05T08:37:20Z","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":"6e839c82dc18a04d378bab8cc701e7e7d4c0cdc98b4436479b35a9e89b5f734a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T12:31:44Z","title_canon_sha256":"0fe355795fa4af62c0938765d615f9b062cf6b9b63f383cc1a5e8ef3ebbaa667"},"schema_version":"1.0","source":{"id":"2406.09972","kind":"arxiv","version":1}},"canonical_sha256":"618222d3afa5ccf8dcc8737d1eb90d23f62b83b24071bbd70d27ce069eee3057","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"618222d3afa5ccf8dcc8737d1eb90d23f62b83b24071bbd70d27ce069eee3057","first_computed_at":"2026-07-05T08:37:20.475923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:20.475923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"djTSXy1WzlFDGR8J5zGfhySwG1eTuwdRa5nMJLC58lO01C2JOYmhliyGnOGFdypIE4JX5YJfPsxlnqfY0LVBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:20.476261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:796a0d67aace8c512a2b9bdad01b2545cdb73240af828fbc6434b23c03f35551","sha256:e3c7f4f85975e33787284620eda590a936a11e181cb3e8c3e856d99215f1a061"],"state_sha256":"b6bba3a1e313ebd89c136f372c2a18e27376ac2adc3fd8dfc397dfd582f26ed5"}