{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6375IGY2T74S53VQH3IRNL5R5E","short_pith_number":"pith:6375IGY2","schema_version":"1.0","canonical_sha256":"f6ffd41b1a9ff92eeeb03ed116afb1e904d0cdee970a7e27d39f351301407168","source":{"kind":"arxiv","id":"2502.12052","version":2},"attestation_state":"computed","paper":{"title":"A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Li Lin, Mingqi Gao, Xiaojun Wan, Xinyu Hu, Zhenghan Yu","submitted_at":"2025-02-17T17:22:49Z","abstract_excerpt":"In NLG meta-evaluation, evaluation metrics are typically assessed based on their consistency with humans. However, we identify some limitations in traditional NLG meta-evaluation approaches, such as issues in handling human ratings and ambiguous selections of correlation measures, which undermine the effectiveness of meta-evaluation. In this work, we propose a dual-perspective NLG meta-evaluation framework that focuses on different evaluation capabilities, thereby providing better interpretability. In addition, we introduce a method of automatically constructing the corresponding benchmarks wi"},"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":"2502.12052","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:22:49Z","cross_cats_sorted":[],"title_canon_sha256":"35e694fcddcbf91ef4911ed5f673fa8430fb1f72bd802b5aacf6da7a799176de","abstract_canon_sha256":"fb0e1be2e440624312c7f250cc951d8340e282f09dc0c9131413f23823dff13b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:29.606180Z","signature_b64":"W41H/qNNNP+dfidefVDj0l/gKwZaqhe4Vo4aBeWU9QWgvrUQsdaG5afiiGjrJC9hTR2tzwp6+HQchE+zREu0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ffd41b1a9ff92eeeb03ed116afb1e904d0cdee970a7e27d39f351301407168","last_reissued_at":"2026-07-05T11:54:29.605640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:29.605640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Li Lin, Mingqi Gao, Xiaojun Wan, Xinyu Hu, Zhenghan Yu","submitted_at":"2025-02-17T17:22:49Z","abstract_excerpt":"In NLG meta-evaluation, evaluation metrics are typically assessed based on their consistency with humans. However, we identify some limitations in traditional NLG meta-evaluation approaches, such as issues in handling human ratings and ambiguous selections of correlation measures, which undermine the effectiveness of meta-evaluation. In this work, we propose a dual-perspective NLG meta-evaluation framework that focuses on different evaluation capabilities, thereby providing better interpretability. In addition, we introduce a method of automatically constructing the corresponding benchmarks wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12052","kind":"arxiv","version":2},"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/2502.12052/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":"2502.12052","created_at":"2026-07-05T11:54:29.605710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12052v2","created_at":"2026-07-05T11:54:29.605710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12052","created_at":"2026-07-05T11:54:29.605710+00:00"},{"alias_kind":"pith_short_12","alias_value":"6375IGY2T74S","created_at":"2026-07-05T11:54:29.605710+00:00"},{"alias_kind":"pith_short_16","alias_value":"6375IGY2T74S53VQ","created_at":"2026-07-05T11:54:29.605710+00:00"},{"alias_kind":"pith_short_8","alias_value":"6375IGY2","created_at":"2026-07-05T11:54:29.605710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E","json":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E.json","graph_json":"https://pith.science/api/pith-number/6375IGY2T74S53VQH3IRNL5R5E/graph.json","events_json":"https://pith.science/api/pith-number/6375IGY2T74S53VQH3IRNL5R5E/events.json","paper":"https://pith.science/paper/6375IGY2"},"agent_actions":{"view_html":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E","download_json":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E.json","view_paper":"https://pith.science/paper/6375IGY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12052&json=true","fetch_graph":"https://pith.science/api/pith-number/6375IGY2T74S53VQH3IRNL5R5E/graph.json","fetch_events":"https://pith.science/api/pith-number/6375IGY2T74S53VQH3IRNL5R5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E/action/storage_attestation","attest_author":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E/action/author_attestation","sign_citation":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E/action/citation_signature","submit_replication":"https://pith.science/pith/6375IGY2T74S53VQH3IRNL5R5E/action/replication_record"}},"created_at":"2026-07-05T11:54:29.605710+00:00","updated_at":"2026-07-05T11:54:29.605710+00:00"}