{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZHYJ5H46FDEGLOJUB5EVZGXO2Y","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":"f466c1ffca30846db49129d99685aad5ced8eb939121e8a9d4124f8e1eaca46e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:53:29Z","title_canon_sha256":"9db56a87b31e44b97e559b7d39eef53fd2982d946e2bac17ab555e61fe737404"},"schema_version":"1.0","source":{"id":"2305.15067","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15067","created_at":"2026-07-05T08:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15067v3","created_at":"2026-07-05T08:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15067","created_at":"2026-07-05T08:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"ZHYJ5H46FDEG","created_at":"2026-07-05T08:23:09Z"},{"alias_kind":"pith_short_16","alias_value":"ZHYJ5H46FDEGLOJU","created_at":"2026-07-05T08:23:09Z"},{"alias_kind":"pith_short_8","alias_value":"ZHYJ5H46","created_at":"2026-07-05T08:23:09Z"}],"graph_snapshots":[{"event_id":"sha256:7decf3ab1086a1ae5b7ceacbf76fe99d608cfeb9a9daeeec7bc719ea3c89153d","target":"graph","created_at":"2026-07-05T08:23:09Z","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/2305.15067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most research about natural language generation (NLG) relies on evaluation benchmarks with limited references for a sample, which may result in poor correlations with human judgements. The underlying reason is that one semantic meaning can actually be expressed in different forms, and the evaluation with a single or few references may not accurately reflect the quality of the model's hypotheses. To address this issue, this paper presents a simple and effective method, named Div-Ref, to enhance existing evaluation benchmarks by enriching the number of references. We leverage large language mode","authors_text":"Dongdong Zhang, Furu Wei, Haoyang Huang, Hongyuan Lu, Tianyi Tang, Tom Kocmi, Wayne Xin Zhao, Yuchen Eleanor Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:53:29Z","title":"Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15067","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:e4c9c037f207de0f8e242dcf7e035656e4e1006df439eaeaefd59a4acfd3a5b2","target":"record","created_at":"2026-07-05T08:23:09Z","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":"f466c1ffca30846db49129d99685aad5ced8eb939121e8a9d4124f8e1eaca46e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:53:29Z","title_canon_sha256":"9db56a87b31e44b97e559b7d39eef53fd2982d946e2bac17ab555e61fe737404"},"schema_version":"1.0","source":{"id":"2305.15067","kind":"arxiv","version":3}},"canonical_sha256":"c9f09e9f9e28c865b9340f495c9aeed636af6ef39f38bc95d57f27efcfffa43b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9f09e9f9e28c865b9340f495c9aeed636af6ef39f38bc95d57f27efcfffa43b","first_computed_at":"2026-07-05T08:23:09.143439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:09.143439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"99gfp6aj5h/8XI+T1RY8dsxxPY/tSDvlB5jejiKoPuI4YmBoDM+zR9ZjlxX1kjYQ05r6CH1k7aVYHXauOKdsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:09.143922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15067","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4c9c037f207de0f8e242dcf7e035656e4e1006df439eaeaefd59a4acfd3a5b2","sha256:7decf3ab1086a1ae5b7ceacbf76fe99d608cfeb9a9daeeec7bc719ea3c89153d"],"state_sha256":"d77d571f5710109356e53c6ab8524cf1a8cc7a8fb46cd33da71266f648f72722"}