{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:56S3U363HXPVUVUGUFZ4TYMWF3","short_pith_number":"pith:56S3U363","schema_version":"1.0","canonical_sha256":"efa5ba6fdb3ddf5a5686a173c9e1962edafbe71c77d67cd53cad2fcfe6d266cd","source":{"kind":"arxiv","id":"2406.12419","version":3},"attestation_state":"computed","paper":{"title":"AI-Assisted Human Evaluation of Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mrinmaya Sachan, Tom Kocmi, Vil\\'em Zouhar","submitted_at":"2024-06-18T09:12:11Z","abstract_excerpt":"Annually, research teams spend large amounts of money to evaluate the quality of machine translation systems (WMT, inter alia). This is expensive because it requires a lot of expert human labor. In the recently adopted annotation protocol, Error Span Annotation (ESA), annotators mark erroneous parts of the translation and then assign a final score. A lot of the annotator time is spent on scanning the translation for possible errors. In our work, we help the annotators by pre-filling the error annotations with recall-oriented automatic quality estimation. With this AI assistance, we obtain anno"},"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":"2406.12419","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T09:12:11Z","cross_cats_sorted":[],"title_canon_sha256":"c5d6e55227a8d17b533c3f5d8cae6f19be05f5fa5e665ae918cc9a24afa64ef6","abstract_canon_sha256":"b5665e4007d88035db694004ca683de25088eb2d6dc03c7695ce42f1d16c5ed1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:41.496539Z","signature_b64":"BRmmqQRw1AJE8pRPR9ovdPFDn7zoMSOwAB1TfiWn3encLlJyJIyDJ1+d5GkOz6CbImbk0Z8sbKl8czQnaU5IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efa5ba6fdb3ddf5a5686a173c9e1962edafbe71c77d67cd53cad2fcfe6d266cd","last_reissued_at":"2026-07-05T10:06:41.496066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:41.496066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-Assisted Human Evaluation of Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mrinmaya Sachan, Tom Kocmi, Vil\\'em Zouhar","submitted_at":"2024-06-18T09:12:11Z","abstract_excerpt":"Annually, research teams spend large amounts of money to evaluate the quality of machine translation systems (WMT, inter alia). This is expensive because it requires a lot of expert human labor. In the recently adopted annotation protocol, Error Span Annotation (ESA), annotators mark erroneous parts of the translation and then assign a final score. A lot of the annotator time is spent on scanning the translation for possible errors. In our work, we help the annotators by pre-filling the error annotations with recall-oriented automatic quality estimation. With this AI assistance, we obtain anno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12419","kind":"arxiv","version":3},"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/2406.12419/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":"2406.12419","created_at":"2026-07-05T10:06:41.496123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12419v3","created_at":"2026-07-05T10:06:41.496123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12419","created_at":"2026-07-05T10:06:41.496123+00:00"},{"alias_kind":"pith_short_12","alias_value":"56S3U363HXPV","created_at":"2026-07-05T10:06:41.496123+00:00"},{"alias_kind":"pith_short_16","alias_value":"56S3U363HXPVUVUG","created_at":"2026-07-05T10:06:41.496123+00:00"},{"alias_kind":"pith_short_8","alias_value":"56S3U363","created_at":"2026-07-05T10:06:41.496123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17720","citing_title":"Multilingual Performance Biases of Large Language Models in Education","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3","json":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3.json","graph_json":"https://pith.science/api/pith-number/56S3U363HXPVUVUGUFZ4TYMWF3/graph.json","events_json":"https://pith.science/api/pith-number/56S3U363HXPVUVUGUFZ4TYMWF3/events.json","paper":"https://pith.science/paper/56S3U363"},"agent_actions":{"view_html":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3","download_json":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3.json","view_paper":"https://pith.science/paper/56S3U363","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12419&json=true","fetch_graph":"https://pith.science/api/pith-number/56S3U363HXPVUVUGUFZ4TYMWF3/graph.json","fetch_events":"https://pith.science/api/pith-number/56S3U363HXPVUVUGUFZ4TYMWF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3/action/storage_attestation","attest_author":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3/action/author_attestation","sign_citation":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3/action/citation_signature","submit_replication":"https://pith.science/pith/56S3U363HXPVUVUGUFZ4TYMWF3/action/replication_record"}},"created_at":"2026-07-05T10:06:41.496123+00:00","updated_at":"2026-07-05T10:06:41.496123+00:00"}