{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LPMK44AJROGB5GNTWTX67BEXWG","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":"cd1b5621b5cf7374f86df2f0f39b6cbeb7ec388382525a1425e492005a81a85b","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:36:22Z","title_canon_sha256":"325dbdc2d50483e571ddef1b8552659e39c5a576e038a85a739275a1b3d68006"},"schema_version":"1.0","source":{"id":"2212.10179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10179","created_at":"2026-07-05T05:27:04Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10179v1","created_at":"2026-07-05T05:27:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10179","created_at":"2026-07-05T05:27:04Z"},{"alias_kind":"pith_short_12","alias_value":"LPMK44AJROGB","created_at":"2026-07-05T05:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"LPMK44AJROGB5GNT","created_at":"2026-07-05T05:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"LPMK44AJ","created_at":"2026-07-05T05:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:93d490c9ff5104689a7430ae627c1a38fc1fc6768d2fc17b0f78d06aa7b030f2","target":"graph","created_at":"2026-07-05T05:27:04Z","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/2212.10179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The state-of-the-art language model-based automatic metrics, e.g. BARTScore, benefiting from large-scale contextualized pre-training, have been successfully used in a wide range of natural language generation (NLG) tasks, including machine translation, text summarization, and data-to-text. Recent studies show that considering both major errors (e.g. mistranslated tokens) and minor errors (e.g. imperfections in fluency) can produce high-quality human judgments. This inspires us to approach the final goal of the evaluation metrics (human-like evaluations) by automatic error analysis. To this end","authors_text":"Dacheng Tao, Derek F. Wong, Kanjian Zhang, Liang Ding, Liping Xie, Qingyu Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:36:22Z","title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10179","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":"sha256:0b8f675c7260b0e0588054ff75f34074f9ac135d6edd46270c107526ba5d7f7e","target":"record","created_at":"2026-07-05T05:27:04Z","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":"cd1b5621b5cf7374f86df2f0f39b6cbeb7ec388382525a1425e492005a81a85b","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:36:22Z","title_canon_sha256":"325dbdc2d50483e571ddef1b8552659e39c5a576e038a85a739275a1b3d68006"},"schema_version":"1.0","source":{"id":"2212.10179","kind":"arxiv","version":1}},"canonical_sha256":"5bd8ae70098b8c1e99b3b4efef8497b19cda346fe65135ba3dd4a08e775b312f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bd8ae70098b8c1e99b3b4efef8497b19cda346fe65135ba3dd4a08e775b312f","first_computed_at":"2026-07-05T05:27:04.839495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:04.839495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HQp7Ls40YZVf4LekR3ZoVHkxUkh8viJ6lZWJn+3Ho3fe9iWqmbjkhSC1Syc+RC+igWzRjpPdP9uGsaYtfyG1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:04.839898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b8f675c7260b0e0588054ff75f34074f9ac135d6edd46270c107526ba5d7f7e","sha256:93d490c9ff5104689a7430ae627c1a38fc1fc6768d2fc17b0f78d06aa7b030f2"],"state_sha256":"af72be4f27669253dfe74ce63e4044cd455a7fc7445ebc793637b30107c5d0a3"}