{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4BXVANW4S3FIRZNBOFC4Q2ZBZZ","short_pith_number":"pith:4BXVANW4","schema_version":"1.0","canonical_sha256":"e06f5036dc96ca88e5a17145c86b21ce4502ac62d102dfe9b9bb9a06944d63eb","source":{"kind":"arxiv","id":"2408.09169","version":1},"attestation_state":"computed","paper":{"title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adarsa Sivaprasad, Albert Gatt, David M. Howcroft, Dimitra Gkatzia, Ond\\v{r}ej Du\\v{s}ek, Ond\\v{r}ej Pl\\'atek, Patr\\'icia Schmidtov\\'a, Saad Mahamood, Simone Balloccu","submitted_at":"2024-08-17T11:13:10Z","abstract_excerpt":"Automatic metrics are extensively used to evaluate natural language processing systems. However, there has been increasing focus on how they are used and reported by practitioners within the field. In this paper, we have conducted a survey on the use of automatic metrics, focusing particularly on natural language generation (NLG) tasks. We inspect which metrics are used as well as why they are chosen and how their use is reported. Our findings from this survey reveal significant shortcomings, including inappropriate metric usage, lack of implementation details and missing correlations with hum"},"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":"2408.09169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-17T11:13:10Z","cross_cats_sorted":[],"title_canon_sha256":"ca7af3fc8b49b04ff6a2f7dc6c0391a7997b3c22cf2a261a0a11a1c2b67f1143","abstract_canon_sha256":"684295b724fa1b2fec46b6dc4d8f380e597325fe708120e2fa23e8e0a63051bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:29.174701Z","signature_b64":"3c8Y+KvW7Cu2wybBWXk/lXcWAbrXSDP/HhCo8E9OulaK7KWYgPSuq2kyOYNURoUPFSyNpyIGHdsMa/rZTPuKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e06f5036dc96ca88e5a17145c86b21ce4502ac62d102dfe9b9bb9a06944d63eb","last_reissued_at":"2026-07-05T08:56:29.174346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:29.174346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adarsa Sivaprasad, Albert Gatt, David M. Howcroft, Dimitra Gkatzia, Ond\\v{r}ej Du\\v{s}ek, Ond\\v{r}ej Pl\\'atek, Patr\\'icia Schmidtov\\'a, Saad Mahamood, Simone Balloccu","submitted_at":"2024-08-17T11:13:10Z","abstract_excerpt":"Automatic metrics are extensively used to evaluate natural language processing systems. However, there has been increasing focus on how they are used and reported by practitioners within the field. In this paper, we have conducted a survey on the use of automatic metrics, focusing particularly on natural language generation (NLG) tasks. We inspect which metrics are used as well as why they are chosen and how their use is reported. Our findings from this survey reveal significant shortcomings, including inappropriate metric usage, lack of implementation details and missing correlations with hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09169","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/2408.09169/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":"2408.09169","created_at":"2026-07-05T08:56:29.174404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09169v1","created_at":"2026-07-05T08:56:29.174404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09169","created_at":"2026-07-05T08:56:29.174404+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BXVANW4S3FI","created_at":"2026-07-05T08:56:29.174404+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BXVANW4S3FIRZNB","created_at":"2026-07-05T08:56:29.174404+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BXVANW4","created_at":"2026-07-05T08:56:29.174404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04815","citing_title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ","json":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ.json","graph_json":"https://pith.science/api/pith-number/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/graph.json","events_json":"https://pith.science/api/pith-number/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/events.json","paper":"https://pith.science/paper/4BXVANW4"},"agent_actions":{"view_html":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ","download_json":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ.json","view_paper":"https://pith.science/paper/4BXVANW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09169&json=true","fetch_graph":"https://pith.science/api/pith-number/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/action/storage_attestation","attest_author":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/action/author_attestation","sign_citation":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/action/citation_signature","submit_replication":"https://pith.science/pith/4BXVANW4S3FIRZNBOFC4Q2ZBZZ/action/replication_record"}},"created_at":"2026-07-05T08:56:29.174404+00:00","updated_at":"2026-07-05T08:56:29.174404+00:00"}