{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LMEEBE27K7TFDG6RUKBRM32UGC","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":"ff9c4e0bac48bf1b003765fb59544099914670fedbca441fbb296d4465858fcb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T12:47:03Z","title_canon_sha256":"2d00563cbedaeee32261adf6c4bb899ff307bdd9be7555fdaee9852920820d88"},"schema_version":"1.0","source":{"id":"1707.06875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06875","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06875v1","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06875","created_at":"2026-05-18T00:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"LMEEBE27K7TF","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LMEEBE27K7TFDG6R","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LMEEBE27","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:4e0ca5f6892f9cf3267ec26670029d519a2c326e9ac7edb132f3b167b210c126","target":"graph","created_at":"2026-05-18T00:35:08Z","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"},"paper":{"abstract_excerpt":"The majority of NLG evaluation relies on automatic metrics, such as BLEU . In this paper, we motivate the need for novel, system- and data-independent automatic evaluation methods: We investigate a wide range of metrics, including state-of-the-art word-based and novel grammar-based ones, and demonstrate that they only weakly reflect human judgements of system outputs as generated by data-driven, end-to-end NLG. We also show that metric performance is data- and system-specific. Nevertheless, our results also suggest that automatic metrics perform reliably at system-level and can support system ","authors_text":"Amanda Cercas Curry, Jekaterina Novikova, Ond\\v{r}ej Du\\v{s}ek, Verena Rieser","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T12:47:03Z","title":"Why We Need New Evaluation Metrics for NLG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06875","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:f0c77ca384255cbabf6903f3fba19f0d7d0eafaa9da21701928fc1a8c55371cb","target":"record","created_at":"2026-05-18T00:35:08Z","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":"ff9c4e0bac48bf1b003765fb59544099914670fedbca441fbb296d4465858fcb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T12:47:03Z","title_canon_sha256":"2d00563cbedaeee32261adf6c4bb899ff307bdd9be7555fdaee9852920820d88"},"schema_version":"1.0","source":{"id":"1707.06875","kind":"arxiv","version":1}},"canonical_sha256":"5b0840935f57e6519bd1a283166f5430a8b2335822f5e1e52f120b69e2d1f67d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b0840935f57e6519bd1a283166f5430a8b2335822f5e1e52f120b69e2d1f67d","first_computed_at":"2026-05-18T00:35:08.965254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:08.965254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u+5NEch+Vlg/By2UtTIzKR7VaKf9SEvzmANVA8N3w+Qr1DLS0Kv+M+MDMjvhSSnlpJfwuaBCv7+YOVdKRtB3DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:08.965626Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0c77ca384255cbabf6903f3fba19f0d7d0eafaa9da21701928fc1a8c55371cb","sha256:4e0ca5f6892f9cf3267ec26670029d519a2c326e9ac7edb132f3b167b210c126"],"state_sha256":"95d805e684b4f43089c8b55e48b8796c1f2b16e89d1133e1916ccf2129ad0e9b"}