{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O6BI5C33AQIDMNMDDLRQYLRUCE","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":"4f8966a2ecfc3c37aa33fa77773b43e88ca161214341afe3ba9217644528ad25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T17:31:46Z","title_canon_sha256":"22c32d715115463b42a6a5948b4f3b42659b35132f018d36328a2af0ed3e092b"},"schema_version":"1.0","source":{"id":"2308.13506","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13506","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13506v2","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13506","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"O6BI5C33AQID","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"O6BI5C33AQIDMNMD","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"O6BI5C33","created_at":"2026-07-05T06:45:20Z"}],"graph_snapshots":[{"event_id":"sha256:0d50fc8e67d9f05542a921495e72c5de31e60d3d6c51a02877680c82882f1bbd","target":"graph","created_at":"2026-07-05T06:45:20Z","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/2308.13506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating paragraph-level data for training and meta-evaluating metrics from existing sentence-level data. Then, we use these new datasets to benchmark existing sentence-level metrics as well as train learned metrics at the paragraph level. Interestingly, our experimental results demonstrate that using sentence-level metrics to score entire paragraphs is equally as eff","authors_text":"Daniel Deutsch, Juraj Juraska, Mara Finkelstein, Markus Freitag","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T17:31:46Z","title":"Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13506","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":"sha256:70d9cf322d28defb9e2981ea574d3f7afe30442f23925249292d73cfe4538f2f","target":"record","created_at":"2026-07-05T06:45:20Z","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":"4f8966a2ecfc3c37aa33fa77773b43e88ca161214341afe3ba9217644528ad25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T17:31:46Z","title_canon_sha256":"22c32d715115463b42a6a5948b4f3b42659b35132f018d36328a2af0ed3e092b"},"schema_version":"1.0","source":{"id":"2308.13506","kind":"arxiv","version":2}},"canonical_sha256":"77828e8b7b04103635831ae30c2e34112a2708fa3991ffdbfa37c23719153885","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77828e8b7b04103635831ae30c2e34112a2708fa3991ffdbfa37c23719153885","first_computed_at":"2026-07-05T06:45:20.226403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:20.226403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ocfbiY8YWiBzrARJGPxZnsY7M38AGO0as7tgqdpQCWMF2ZkxBwpEB+njE3w9+JzJuCzH8E21IboH4NCgzZQjAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:20.226831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13506","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70d9cf322d28defb9e2981ea574d3f7afe30442f23925249292d73cfe4538f2f","sha256:0d50fc8e67d9f05542a921495e72c5de31e60d3d6c51a02877680c82882f1bbd"],"state_sha256":"2985d9ab584eef4c58c3413325baefe2527275209ddb2b06a58cd2af5acdf7a5"}