{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LPMK44AJROGB5GNTWTX67BEXWG","short_pith_number":"pith:LPMK44AJ","schema_version":"1.0","canonical_sha256":"5bd8ae70098b8c1e99b3b4efef8497b19cda346fe65135ba3dd4a08e775b312f","source":{"kind":"arxiv","id":"2212.10179","version":1},"attestation_state":"computed","paper":{"title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Derek F. Wong, Kanjian Zhang, Liang Ding, Liping Xie, Qingyu Lu","submitted_at":"2022-12-20T11:36:22Z","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"},"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":"2212.10179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:36:22Z","cross_cats_sorted":[],"title_canon_sha256":"325dbdc2d50483e571ddef1b8552659e39c5a576e038a85a739275a1b3d68006","abstract_canon_sha256":"cd1b5621b5cf7374f86df2f0f39b6cbeb7ec388382525a1425e492005a81a85b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:04.839898Z","signature_b64":"HQp7Ls40YZVf4LekR3ZoVHkxUkh8viJ6lZWJn+3Ho3fe9iWqmbjkhSC1Syc+RC+igWzRjpPdP9uGsaYtfyG1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bd8ae70098b8c1e99b3b4efef8497b19cda346fe65135ba3dd4a08e775b312f","last_reissued_at":"2026-07-05T05:27:04.839495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:04.839495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Derek F. Wong, Kanjian Zhang, Liang Ding, Liping Xie, Qingyu Lu","submitted_at":"2022-12-20T11:36:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10179","kind":"arxiv","version":1},"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/2212.10179/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":"2212.10179","created_at":"2026-07-05T05:27:04.839545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10179v1","created_at":"2026-07-05T05:27:04.839545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10179","created_at":"2026-07-05T05:27:04.839545+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPMK44AJROGB","created_at":"2026-07-05T05:27:04.839545+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPMK44AJROGB5GNT","created_at":"2026-07-05T05:27:04.839545+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPMK44AJ","created_at":"2026-07-05T05:27:04.839545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG","json":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG.json","graph_json":"https://pith.science/api/pith-number/LPMK44AJROGB5GNTWTX67BEXWG/graph.json","events_json":"https://pith.science/api/pith-number/LPMK44AJROGB5GNTWTX67BEXWG/events.json","paper":"https://pith.science/paper/LPMK44AJ"},"agent_actions":{"view_html":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG","download_json":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG.json","view_paper":"https://pith.science/paper/LPMK44AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10179&json=true","fetch_graph":"https://pith.science/api/pith-number/LPMK44AJROGB5GNTWTX67BEXWG/graph.json","fetch_events":"https://pith.science/api/pith-number/LPMK44AJROGB5GNTWTX67BEXWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG/action/storage_attestation","attest_author":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG/action/author_attestation","sign_citation":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG/action/citation_signature","submit_replication":"https://pith.science/pith/LPMK44AJROGB5GNTWTX67BEXWG/action/replication_record"}},"created_at":"2026-07-05T05:27:04.839545+00:00","updated_at":"2026-07-05T05:27:04.839545+00:00"}