{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:35XGJS3B25HDQD5CXAO4Z6SALL","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":"dffe0fd778666d89d76f3eeb57edffb88dfeb80ebb92142dd128bd2e5a696a58","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T16:49:09Z","title_canon_sha256":"a5ce94c6827b382c27551c73a36f96dc3bbfcc7b34759485a78eb5561256af7d"},"schema_version":"1.0","source":{"id":"2004.06063","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06063","created_at":"2026-07-05T01:44:10Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06063v2","created_at":"2026-07-05T01:44:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06063","created_at":"2026-07-05T01:44:10Z"},{"alias_kind":"pith_short_12","alias_value":"35XGJS3B25HD","created_at":"2026-07-05T01:44:10Z"},{"alias_kind":"pith_short_16","alias_value":"35XGJS3B25HDQD5C","created_at":"2026-07-05T01:44:10Z"},{"alias_kind":"pith_short_8","alias_value":"35XGJS3B","created_at":"2026-07-05T01:44:10Z"}],"graph_snapshots":[{"event_id":"sha256:98c5328c380ce9cc26fc1aee80a8f6e8bfe61a278148060465f9facbc3151353","target":"graph","created_at":"2026-07-05T01:44:10Z","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/2004.06063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice of metric is important, the nature of the references is also critical. We study different methods to collect references and compare their value in automated evaluation by reporting correlation with human evaluation for a variety of systems and metrics. Motivated by the finding that typical references exhibit poor diversity, concentrating around translationese language, we develop a paraphrasing task for linguists to","authors_text":"David Grangier, Isaac Caswell, Markus Freitag","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T16:49:09Z","title":"BLEU might be Guilty but References are not Innocent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06063","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:eb1967021328269ddd7889f22c59279794c28ff95f38f62d14cd9c270d7d3ed2","target":"record","created_at":"2026-07-05T01:44:10Z","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":"dffe0fd778666d89d76f3eeb57edffb88dfeb80ebb92142dd128bd2e5a696a58","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T16:49:09Z","title_canon_sha256":"a5ce94c6827b382c27551c73a36f96dc3bbfcc7b34759485a78eb5561256af7d"},"schema_version":"1.0","source":{"id":"2004.06063","kind":"arxiv","version":2}},"canonical_sha256":"df6e64cb61d74e380fa2b81dccfa405aeac482d590bf62307e5720199762b8ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df6e64cb61d74e380fa2b81dccfa405aeac482d590bf62307e5720199762b8ab","first_computed_at":"2026-07-05T01:44:10.935446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:10.935446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SLDV9ZsQlqRqLgnJDzvf51b9jECDaeBkjmxDCOLAEydcn75BZwWRdW54Yt4EXWBTVI9SrHUZs6gDlaS7nPmlAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:10.935936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.06063","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb1967021328269ddd7889f22c59279794c28ff95f38f62d14cd9c270d7d3ed2","sha256:98c5328c380ce9cc26fc1aee80a8f6e8bfe61a278148060465f9facbc3151353"],"state_sha256":"eba2b464d5ad18869f90abd41fc1eb7acca8a7946482c90c82f0ca466e406502"}