{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MXISMG2VKH2DZSMHYO4BTORJ3C","short_pith_number":"pith:MXISMG2V","schema_version":"1.0","canonical_sha256":"65d1261b5551f43cc987c3b819ba29d893690fec1140520a447c6a15ee389a86","source":{"kind":"arxiv","id":"2406.07935","version":1},"attestation_state":"computed","paper":{"title":"Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jie Ruan, Wenqing Wang, Xiaojun Wan","submitted_at":"2024-06-12T06:59:31Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.07935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T06:59:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"628292e06a7923db3c243941808ae6f33fffcfef4871709efdaab8e0ecfa60da","abstract_canon_sha256":"240cd08cf90b8a96c3a452fc68fdfdb1614fcecc1de768b17a68dcc22a17e47f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:40.857079Z","signature_b64":"Dzrrq/Z/3E4F1fVN9E8qiXFvH1KuRhx5YCcQGEgopdxGKHB+NdoTTylgCYkwuCyfQ69I8T9awskVnzq0+xQyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d1261b5551f43cc987c3b819ba29d893690fec1140520a447c6a15ee389a86","last_reissued_at":"2026-07-05T08:30:40.856472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:40.856472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jie Ruan, Wenqing Wang, Xiaojun Wan","submitted_at":"2024-06-12T06:59:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07935","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.07935/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.07935","created_at":"2026-07-05T08:30:40.856540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07935v1","created_at":"2026-07-05T08:30:40.856540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07935","created_at":"2026-07-05T08:30:40.856540+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXISMG2VKH2D","created_at":"2026-07-05T08:30:40.856540+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXISMG2VKH2DZSMH","created_at":"2026-07-05T08:30:40.856540+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXISMG2V","created_at":"2026-07-05T08:30:40.856540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03637","citing_title":"RewardAnything: Generalizable Principle-Following Reward Models","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C","json":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C.json","graph_json":"https://pith.science/api/pith-number/MXISMG2VKH2DZSMHYO4BTORJ3C/graph.json","events_json":"https://pith.science/api/pith-number/MXISMG2VKH2DZSMHYO4BTORJ3C/events.json","paper":"https://pith.science/paper/MXISMG2V"},"agent_actions":{"view_html":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C","download_json":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C.json","view_paper":"https://pith.science/paper/MXISMG2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07935&json=true","fetch_graph":"https://pith.science/api/pith-number/MXISMG2VKH2DZSMHYO4BTORJ3C/graph.json","fetch_events":"https://pith.science/api/pith-number/MXISMG2VKH2DZSMHYO4BTORJ3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C/action/storage_attestation","attest_author":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C/action/author_attestation","sign_citation":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C/action/citation_signature","submit_replication":"https://pith.science/pith/MXISMG2VKH2DZSMHYO4BTORJ3C/action/replication_record"}},"created_at":"2026-07-05T08:30:40.856540+00:00","updated_at":"2026-07-05T08:30:40.856540+00:00"}