{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MXISMG2VKH2DZSMHYO4BTORJ3C","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":"240cd08cf90b8a96c3a452fc68fdfdb1614fcecc1de768b17a68dcc22a17e47f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T06:59:31Z","title_canon_sha256":"628292e06a7923db3c243941808ae6f33fffcfef4871709efdaab8e0ecfa60da"},"schema_version":"1.0","source":{"id":"2406.07935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07935","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07935v1","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07935","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"MXISMG2VKH2D","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"MXISMG2VKH2DZSMH","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"MXISMG2V","created_at":"2026-07-05T08:30:40Z"}],"graph_snapshots":[{"event_id":"sha256:3f2dc5e491cb30b82217aa6741d6061307c0b0ee83a70d3ab8ec99d8df387b79","target":"graph","created_at":"2026-07-05T08:30:40Z","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/2406.07935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human evaluation serves as the gold standard for assessing the quality of Natural Language Generation (NLG) systems. Nevertheless, the evaluation guideline, as a pivotal element ensuring reliable and reproducible human assessment, has received limited attention.Our investigation revealed that only 29.84% of recent papers involving human evaluation at top conferences release their evaluation guidelines, with vulnerabilities identified in 77.09% of these guidelines. Unreliable evaluation guidelines can yield inaccurate assessment outcomes, potentially impeding the advancement of NLG in the right","authors_text":"Jie Ruan, Wenqing Wang, Xiaojun Wan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T06:59:31Z","title":"Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07935","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":"sha256:9fe80bfc8ce52d93961d6d8a2943c207173a15ac073efabcbddd29e4f25c3730","target":"record","created_at":"2026-07-05T08:30:40Z","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":"240cd08cf90b8a96c3a452fc68fdfdb1614fcecc1de768b17a68dcc22a17e47f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T06:59:31Z","title_canon_sha256":"628292e06a7923db3c243941808ae6f33fffcfef4871709efdaab8e0ecfa60da"},"schema_version":"1.0","source":{"id":"2406.07935","kind":"arxiv","version":1}},"canonical_sha256":"65d1261b5551f43cc987c3b819ba29d893690fec1140520a447c6a15ee389a86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65d1261b5551f43cc987c3b819ba29d893690fec1140520a447c6a15ee389a86","first_computed_at":"2026-07-05T08:30:40.856472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:40.856472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dzrrq/Z/3E4F1fVN9E8qiXFvH1KuRhx5YCcQGEgopdxGKHB+NdoTTylgCYkwuCyfQ69I8T9awskVnzq0+xQyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:40.857079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fe80bfc8ce52d93961d6d8a2943c207173a15ac073efabcbddd29e4f25c3730","sha256:3f2dc5e491cb30b82217aa6741d6061307c0b0ee83a70d3ab8ec99d8df387b79"],"state_sha256":"2c282f86687e22eceb6351b5a1ab36b07c7e1f252ff751e101946bd947cf6f6a"}