{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E4GRGVJVIZ5ZK5AAO4IN4V4HT7","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":"09775161148d80a3eba4677266a267d6c759800504cbe68cb250b5feb50c0907","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-21T17:05:54Z","title_canon_sha256":"58a91a92613b3bd322eb44341289415b1b53840d3778ab12dd165e2472f851da"},"schema_version":"1.0","source":{"id":"2203.11131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.11131","created_at":"2026-07-05T04:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2203.11131v1","created_at":"2026-07-05T04:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11131","created_at":"2026-07-05T04:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"E4GRGVJVIZ5Z","created_at":"2026-07-05T04:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"E4GRGVJVIZ5ZK5AA","created_at":"2026-07-05T04:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"E4GRGVJV","created_at":"2026-07-05T04:07:00Z"}],"graph_snapshots":[{"event_id":"sha256:b3704bb16c836210a5c356c79e423db2890320bcd9f8fdb4d1b3fd72e62a2b6c","target":"graph","created_at":"2026-07-05T04:07:00Z","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/2203.11131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics (such as BERTScore or MoverScore) are based on black-box language models such as BERT or XLM-R. They often achieve strong correlations with human judgments, but recent research indicates that the lower-quality classical metrics remain dominant, one of the potential reasons being that their decision processes are transparent. To foster more widespread acceptance of the novel high-quality metrics, explainability thus becomes crucial. In this concept paper, we identify key properties and propose key goals of ex","authors_text":"Christoph Leiter, Marina Fomicheva, Piyawat Lertvittayakumjorn, Steffen Eger, Wei Zhao, Yang Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-21T17:05:54Z","title":"Towards Explainable Evaluation Metrics for Natural Language Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11131","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:cefb73287a1d2e9c3b3f39d7ba96f2097d62721fe72889dee48af43c9579ec3e","target":"record","created_at":"2026-07-05T04:07:00Z","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":"09775161148d80a3eba4677266a267d6c759800504cbe68cb250b5feb50c0907","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-21T17:05:54Z","title_canon_sha256":"58a91a92613b3bd322eb44341289415b1b53840d3778ab12dd165e2472f851da"},"schema_version":"1.0","source":{"id":"2203.11131","kind":"arxiv","version":1}},"canonical_sha256":"270d135535467b9574007710de57879fea3e9a85eec0e01f94f1b89f99683618","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"270d135535467b9574007710de57879fea3e9a85eec0e01f94f1b89f99683618","first_computed_at":"2026-07-05T04:07:00.969368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:00.969368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0oTuYM0KPaOoQAj6cbRGGWXTvir8zTht5lZKaYykYamHBvHYuFAVCHQ29bAIJvRWeYjIDgWlL77UJTBT4kE3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:00.969824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.11131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cefb73287a1d2e9c3b3f39d7ba96f2097d62721fe72889dee48af43c9579ec3e","sha256:b3704bb16c836210a5c356c79e423db2890320bcd9f8fdb4d1b3fd72e62a2b6c"],"state_sha256":"ac3e1808d650a697ced5c1239540f75680da667ca7b333a0122f380aa2eb4ec5"}