{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6375IGY2T74S53VQH3IRNL5R5E","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":"fb0e1be2e440624312c7f250cc951d8340e282f09dc0c9131413f23823dff13b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:22:49Z","title_canon_sha256":"35e694fcddcbf91ef4911ed5f673fa8430fb1f72bd802b5aacf6da7a799176de"},"schema_version":"1.0","source":{"id":"2502.12052","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12052","created_at":"2026-07-05T11:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12052v2","created_at":"2026-07-05T11:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12052","created_at":"2026-07-05T11:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"6375IGY2T74S","created_at":"2026-07-05T11:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"6375IGY2T74S53VQ","created_at":"2026-07-05T11:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"6375IGY2","created_at":"2026-07-05T11:54:29Z"}],"graph_snapshots":[{"event_id":"sha256:aa1cc9407e4d9a31cc5e796ad65aa1d65fb52537db20cab419c12ff68878d285","target":"graph","created_at":"2026-07-05T11:54:29Z","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/2502.12052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Li Lin, Mingqi Gao, Xiaojun Wan, Xinyu Hu, Zhenghan Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:22:49Z","title":"A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12052","kind":"arxiv","version":2},"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:ac35e610ea3d7b2f52b26e7bd5af40f24d0e423aea12ec7b81e26f4388a4d5eb","target":"record","created_at":"2026-07-05T11:54:29Z","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":"fb0e1be2e440624312c7f250cc951d8340e282f09dc0c9131413f23823dff13b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:22:49Z","title_canon_sha256":"35e694fcddcbf91ef4911ed5f673fa8430fb1f72bd802b5aacf6da7a799176de"},"schema_version":"1.0","source":{"id":"2502.12052","kind":"arxiv","version":2}},"canonical_sha256":"f6ffd41b1a9ff92eeeb03ed116afb1e904d0cdee970a7e27d39f351301407168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6ffd41b1a9ff92eeeb03ed116afb1e904d0cdee970a7e27d39f351301407168","first_computed_at":"2026-07-05T11:54:29.605640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:29.605640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W41H/qNNNP+dfidefVDj0l/gKwZaqhe4Vo4aBeWU9QWgvrUQsdaG5afiiGjrJC9hTR2tzwp6+HQchE+zREu0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:29.606180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12052","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac35e610ea3d7b2f52b26e7bd5af40f24d0e423aea12ec7b81e26f4388a4d5eb","sha256:aa1cc9407e4d9a31cc5e796ad65aa1d65fb52537db20cab419c12ff68878d285"],"state_sha256":"21d3dbf58af62ee3ed6004b0e4e414eb960bb4f9878ec3537b81e3f86049c684"}