{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VTDOT6BYTS65S5VWQDXWZPIWKB","short_pith_number":"pith:VTDOT6BY","schema_version":"1.0","canonical_sha256":"acc6e9f8389cbdd976b680ef6cbd16507840c1403a7ded8332429747142c2aee","source":{"kind":"arxiv","id":"2601.07648","version":2},"attestation_state":"computed","paper":{"title":"What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charlott Jakob, David Schlangen, Eleni Metheniti, Jing Yang, Konrad Rieck, Leonhard Hennig, Nils Feldhus, Qianli Wang, Salar Mohtaj, Sebastian M\\\"oller, Sherzod Hakimov, Vera Schmitt, Veronika Solopova","submitted_at":"2026-01-12T15:27:58Z","abstract_excerpt":"As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) adoption has accelerated rapidly, appearing in more papers than human evaluation in 2025. This pivotal shift motivates a critical analysis of current evaluation practices. Overcoming the limits of rigid keyword filtering and manual review, we employ a multi-LLM information extraction pipeline to gather structured metadata from 14,171 papers across four major NLP conferences (2020-2025). Analyzing 3,334 filtered NLG papers, we identify three systemic "},"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":"2601.07648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T15:27:58Z","cross_cats_sorted":[],"title_canon_sha256":"9254acd717a998162df67acd4704d5d6edec01821abc296c5b8ff409b69e532e","abstract_canon_sha256":"e71a72aa90d7f1a13716266456aa4aa43cdf9c40cc7851803e601ee0e33a8973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:11.405560Z","signature_b64":"byZCYioQIJLnUZQHczgPBjBMk6618GjDOqoBqsHAj8XBrMLlcN/eCg926+MHOk7tZCOiVI/Q4SCvrbhTHc8/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc6e9f8389cbdd976b680ef6cbd16507840c1403a7ded8332429747142c2aee","last_reissued_at":"2026-05-28T01:05:11.405073Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:11.405073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charlott Jakob, David Schlangen, Eleni Metheniti, Jing Yang, Konrad Rieck, Leonhard Hennig, Nils Feldhus, Qianli Wang, Salar Mohtaj, Sebastian M\\\"oller, Sherzod Hakimov, Vera Schmitt, Veronika Solopova","submitted_at":"2026-01-12T15:27:58Z","abstract_excerpt":"As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) adoption has accelerated rapidly, appearing in more papers than human evaluation in 2025. This pivotal shift motivates a critical analysis of current evaluation practices. Overcoming the limits of rigid keyword filtering and manual review, we employ a multi-LLM information extraction pipeline to gather structured metadata from 14,171 papers across four major NLP conferences (2020-2025). Analyzing 3,334 filtered NLG papers, we identify three systemic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07648","kind":"arxiv","version":2},"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/2601.07648/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":"2601.07648","created_at":"2026-05-28T01:05:11.405139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.07648v2","created_at":"2026-05-28T01:05:11.405139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07648","created_at":"2026-05-28T01:05:11.405139+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTDOT6BYTS65","created_at":"2026-05-28T01:05:11.405139+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTDOT6BYTS65S5VW","created_at":"2026-05-28T01:05:11.405139+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTDOT6BY","created_at":"2026-05-28T01:05:11.405139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB","json":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB.json","graph_json":"https://pith.science/api/pith-number/VTDOT6BYTS65S5VWQDXWZPIWKB/graph.json","events_json":"https://pith.science/api/pith-number/VTDOT6BYTS65S5VWQDXWZPIWKB/events.json","paper":"https://pith.science/paper/VTDOT6BY"},"agent_actions":{"view_html":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB","download_json":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB.json","view_paper":"https://pith.science/paper/VTDOT6BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.07648&json=true","fetch_graph":"https://pith.science/api/pith-number/VTDOT6BYTS65S5VWQDXWZPIWKB/graph.json","fetch_events":"https://pith.science/api/pith-number/VTDOT6BYTS65S5VWQDXWZPIWKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB/action/storage_attestation","attest_author":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB/action/author_attestation","sign_citation":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB/action/citation_signature","submit_replication":"https://pith.science/pith/VTDOT6BYTS65S5VWQDXWZPIWKB/action/replication_record"}},"created_at":"2026-05-28T01:05:11.405139+00:00","updated_at":"2026-05-28T01:05:11.405139+00:00"}