{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTDOT6BYTS65S5VWQDXWZPIWKB","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":"e71a72aa90d7f1a13716266456aa4aa43cdf9c40cc7851803e601ee0e33a8973","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T15:27:58Z","title_canon_sha256":"9254acd717a998162df67acd4704d5d6edec01821abc296c5b8ff409b69e532e"},"schema_version":"1.0","source":{"id":"2601.07648","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.07648","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2601.07648v2","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07648","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"VTDOT6BYTS65","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"VTDOT6BYTS65S5VW","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"VTDOT6BY","created_at":"2026-05-28T01:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:81cf97600579d1c666c14b7f56a9c07640b9eedf5d80f495bf09f67f3de24f19","target":"graph","created_at":"2026-05-28T01:05:11Z","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/2601.07648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T15:27:58Z","title":"What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07648","kind":"arxiv","version":2},"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:c5eac9e7372641457889968b4541f13d4f71722cb2b1dcd20866d78cb101e292","target":"record","created_at":"2026-05-28T01:05:11Z","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":"e71a72aa90d7f1a13716266456aa4aa43cdf9c40cc7851803e601ee0e33a8973","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T15:27:58Z","title_canon_sha256":"9254acd717a998162df67acd4704d5d6edec01821abc296c5b8ff409b69e532e"},"schema_version":"1.0","source":{"id":"2601.07648","kind":"arxiv","version":2}},"canonical_sha256":"acc6e9f8389cbdd976b680ef6cbd16507840c1403a7ded8332429747142c2aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc6e9f8389cbdd976b680ef6cbd16507840c1403a7ded8332429747142c2aee","first_computed_at":"2026-05-28T01:05:11.405073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:11.405073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"byZCYioQIJLnUZQHczgPBjBMk6618GjDOqoBqsHAj8XBrMLlcN/eCg926+MHOk7tZCOiVI/Q4SCvrbhTHc8/Dg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:11.405560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.07648","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5eac9e7372641457889968b4541f13d4f71722cb2b1dcd20866d78cb101e292","sha256:81cf97600579d1c666c14b7f56a9c07640b9eedf5d80f495bf09f67f3de24f19"],"state_sha256":"2a910a9d01626c63db50ef70914641f2c0f3d39e6aa6fffd90636f6bc8a73485"}